HLL 0.1-TX
Grades, item by item
Every graded answer, every axis, every citation check. Scores are mechanical and recomputable. Public-split items show the blinded facts and the model's full answer; private-split items show scores and notes only. Weights: Standard 2, Authority 2, Outcome 2, Quote fidelity 2. A fabricated citation caps the item at 25%.
watch live|all runsdeepseek/deepseek-v4-flash · rawdeepseek/deepseek-v4-flash · juiceddeepseek/deepseek-v4-flash · dr2upstage/solar-pro4 · rawupstage/solar-pro4 · dr2openai/gpt-oss-120b · rawopenai/gpt-oss-20b · rawopenai/gpt-oss-120b · dr2openai/gpt-oss-20b · dr2google/gemini-3.7-flash · rawgoogle/gemini-3.7-flash · dr2
administrativeappellate-mandamusappellate-procedurearbitrationassault-iiedauto-accidentauto-insurance-uimchild-custodychild-supportcivil-litigationconstitutionalconstructionconsumer-dtpacontractsconversioncps-terminationcriminaldefamationdiscoverydivorce-propertyeasements-boundarieselectionseminent-domainemploymentevictionevidencefamilyforeclosurefraudgovernment-municipalgroundwaterhabeashealthcare-medmalhoa-condohomicideineffective-assistanceinsurancejurisdiction-traplaborlandlord-tenantlegal-malpracticelimitationsnuisance-trespassoil-gasopen-recordsotherpersonal-injurypremises-liabilityprobateproducts-liabilityprofessional-responsibilityreal-estate-brokersreal-propertyschool-lawsearch-seizuresovereign-immunitysummary-judgmenttaxtheft-fraud-crimestorttortious-interferencetruckingvenue-forumworkers-compwrongful-death
25%hll-cl11410171-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority60%×2
Quote fidelity0%×2
Citation checks
found453 S.W.3d 123 · in CourtListener bulk table
unverified345 S.W.3d 456 · verifier rate-limited
found201 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: statements made for medical diagnosis or treatment
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
101575ms · graded 2026-08-28 10:13
0%hll-cl11410163-3arbitrationdifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
180008ms · graded 2026-08-28 10:13
0%hll-cl11410168-2contractsdifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
100392ms · graded 2026-08-28 10:13
17%hll-cl11410168-4contractsdifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome50%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: nonsuited all claims not granted summary judgment.
unsupported for: all claims not granted summary judgment are nonsuited
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
79555ms · graded 2026-08-28 10:13
0%hll-cl11410167-3appellate-proceduredifficulty 3private splitblankopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
86216ms · graded 2026-08-28 10:13
50%hll-cl11410167-2appellate-proceduredifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found71 S.W.3d 1 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
119559ms · graded 2026-08-28 10:13
17%hll-cl11410168-3contractsdifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome50%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: has not produced evidence sufficient to create a genuine issue of material fact.
unsupported for: A party moving for summary judgment must produce evidence that a genuine issue of material fact exists.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
42511ms · graded 2026-08-28 10:12
25%hll-cl11410163-1arbitrationdifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found201 S.W.3d 1 · in CourtListener bulk table
unverified201 S.W.3d 102 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: to correct a clerical error, supply a missing portion, or otherwise clarify the award
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
96284ms · graded 2026-08-28 10:12
25%hll-cl11408286-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found442 S.W.3d 1 · in CourtListener bulk table
found347 U.S. 497 · in DocketRouter index
found507 U.S. 725 · in DocketRouter index
found332 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
no passage507 U.S. 725 for: did not affect the outcome of the trial
unsupported for: communicates the victim’s account of the crime to the police.
unsupported for: the admission of a testimonial victim‑identification video is not automatically reversible; the error must be examined under the harmless‑er
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
172259ms · graded 2026-08-28 10:12
25%hll-cl11410163-2arbitrationdifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found475 U.S. 643 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: A party may move for clarification, correction, or modification of an award within 30 days after receipt of the award.
unsupported for: shall be deemed part of the original award.
unsupported for: A party may file a motion for clarification of the award within 30 days after receipt. The arbitrator may issue a clarification award, which
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
83788ms · graded 2026-08-28 10:12
50%hll-cl11410161-3civil-litigationdifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
89433ms · graded 2026-08-28 10:11
25%hll-cl11410161-4constitutionaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority67%×2
Quote fidelity0%×2
Citation checks
found339 U.S. 306 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
no passage339 U.S. 306 for: Notice must be reasonably calculated to apprise interested parties of the pendency of the action and afford them an opportunity to present t
unsupported for: served in a manner prescribed by the rules
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
85709ms · graded 2026-08-28 10:11
31%hll-cl11410161-1real-propertydifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority63%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
88949ms · graded 2026-08-28 10:11
25%hll-cl11409425-04criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: The trial court may correct a clerical error in a judgment of conviction or sentence.
unsupported for: The appellate court may correct a clerical error in the judgment of the lower court, or may remand for the lower court to correct the error.
unsupported for: black man in a dark sedan who flashed a badge and handcuffs
unsupported for: the prior acts are admissible only to show identity, not to prove propensity
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
60083ms · graded 2026-08-28 10:11
50%hll-cl11409425-03criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
79227ms · graded 2026-08-28 10:10
50%hll-cl11408284-3criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
in opinion556 U.S. 332
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
99431ms · graded 2026-08-28 10:10
50%hll-cl11408286-3criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
in opinion541 U.S. 36
found547 U.S. 813 · in DocketRouter index
unverified2020 U.S. App. LEXIS 12345 · verifier request budget exhausted
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
75816ms · graded 2026-08-28 10:10
25%hll-cl11408280-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: in the light most favorable to the State
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
127074ms · graded 2026-08-28 10:10
50%hll-cl11408284-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found392 U.S. 1 · in DocketRouter index
found440 U.S. 648 · in DocketRouter index
found446 U.S. 544 · in DocketRouter index
unverified514 U.S. 199 · verifier request budget exhausted
in opinion556 U.S. 332
unverified456 U.S. 627 · verifier request budget exhausted
found452 S.W.3d 1 · in DocketRouter index
unverified502 U.S. 220 · verifier request budget exhausted
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
92812ms · graded 2026-08-28 10:10
25%hll-cl11408286-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority60%×2
Quote fidelity0%×2
Citation checks
in opinion541 U.S. 36
unverified509 U.S. 613 · verifier rate-limited
found562 U.S. 344 · in DocketRouter index
found525 S.W.3d 1 · in CourtListener bulk table
unverified386 U.S. 595 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: visual conduct is not a statement within the meaning of *Crawford*.
unsupported for: the evidence of guilt is so overwhelming that it could not have affected the verdict.
unsupported for: depicts a victim’s injuries and the victim’s gestures
unsupported for: her husband struck her with a shower rod
unsupported for: could alone support a conviction beyond a reasonable doubt.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
54849ms · graded 2026-08-28 10:10
25%hll-cl11408283-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: kicked the door and broke a window
unsupported for: grabbed her, shoved her, and took her cell phone.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
86032ms · graded 2026-08-28 10:10
50%hll-cl11408283-4criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
unverified299 S.W.3d 123 · verifier request budget exhausted
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
47814ms · graded 2026-08-28 10:09
25%hll-cl11407948-4appellate-proceduredifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found201 S.W.3d 1 · in CourtListener bulk table
found200 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: If the trial court does not enter an order granting or denying the motion within 75 days after the filing of the motion, the motion is deeme
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
107539ms · graded 2026-08-28 10:09
25%hll-cl11407948-2evidencedifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found201 S.W.3d 1 · in CourtListener bulk table
unverified201 S.W.3d 1025 · verifier request budget exhausted
unverified201 S.W.3d 123 · verifier request budget exhausted
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: will not reverse a trial‑court evidentiary ruling unless it is arbitrary, unreasonable, or manifestly erroneous
unsupported for: clear statement of the issues, a concise statement of the facts, and a discussion of the applicable law with citations
unsupported for: A representative of Dorado Trucking authenticated the contents.
unsupported for: discussion of the applicable law with citations.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
110996ms · graded 2026-08-28 10:09
25%hll-cl11408280-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority58%×2
Quote fidelity0%×2
Citation checks
in opinion443 U.S. 307
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: The question is not whether the evidence is sufficient to prove the defendant’s guilt beyond a reasonable doubt, but whether it is sufficien
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
95988ms · graded 2026-08-28 10:09
25%hll-cl11406805-3criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: has been convicted of a felony
unsupported for: is prohibited from possessing a firearm
unsupported for: the State’s burden is not satisfied by a mere conviction; it must also prove that the defendant was still serving his sentence at the time o
unsupported for: the statutory prohibition is a factual element that must be proved by the State; a failure to prove the release date, when the defendant’s c
unsupported for: the State may rely on the sentencing order and the date of conviction to infer the release date, but the inference must be supported by comp
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
100931ms · graded 2026-08-28 10:08
67%hll-cl11406805-1criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity100%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
supported for: knew the backpack contained the handgun.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
93115ms · graded 2026-08-28 10:08
0%hll-cl11405911-3criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
180008ms · graded 2026-08-28 10:08
19%hll-cl11408280-3criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority58%×2
Quote fidelity0%×2
Citation checks
in opinion443 U.S. 307
found201 S.W.3d 1 · in CourtListener bulk table
unverified201 S.W.3d 100 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: any rational trier of fact could find the defendant guilty beyond a reasonable doubt.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
27438ms · graded 2026-08-28 10:08
50%hll-cl11408280-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found201 S.W.3d 1 · in CourtListener bulk table
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
39815ms · graded 2026-08-28 10:08
0%hll-cl11405924-3healthcare-medmaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found352 S.W.3d 1 · in CourtListener bulk table
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
139765ms · graded 2026-08-28 10:08
25%hll-cl11406805-4criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: Not on His Own Premises or in His Own Vehicle
unsupported for: A judgment of conviction shall be reversed if the evidence, when viewed in the light most favorable to the State, is insufficient to sustain
unsupported for: if the person is not a law‑enforcement officer and the person is not on his own premises or in his own vehicle.
unsupported for: in the light most favorable to the State
unsupported for: any real property, including a building, structure, or land, and any personal property that is attached to or a part of the real property.
unsupported for: not on his own premises or in his own vehicle
unsupported for: public sidewalk = not own premises
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
17881ms · graded 2026-08-28 10:07
25%hll-cl11406802-3criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the admission of prior bad acts that are offered solely to show a defendant’s propensity is a classic example of a Rule 403 error
unsupported for: plain‑error review is a narrow gateway; the error must be clear and affect the trial’s fairness
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
44120ms · graded 2026-08-28 10:07
25%hll-cl11406800-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found100 S.W.3d 1 · in CourtListener bulk table
unverified200 S.W.3d 123 · verifier request budget exhausted
unverified200 S.W.3d 456 · verifier request budget exhausted
unverified200 S.W.3d 789 · verifier request budget exhausted
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: The trial court shall consider the jury’s sentencing recommendation and shall inform the jury of the effect of its recommendation.
unsupported for: deprives the jury of the information it needs to render a meaningful recommendation
unsupported for: The court shall specify in a written order the manner in which the sentences are to be served, and the order must be consistent with the ora
unsupported for: Counts I‑IV will be cumulative (i.e., consecutive); counts V‑VIII will run concurrently with those.
unsupported for: Sequence of counts I‑IV and confirming counts I, V, VI, VII, VIII will run concurrently.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
88230ms · graded 2026-08-28 10:07
25%hll-cl11406802-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: propensity to commit the charged conduct.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
48658ms · graded 2026-08-28 10:07
25%hll-cl11406800-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found115 S.W.3d 1 · in DocketRouter index
unverified124 S.W.3d 123 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: The court shall not answer any question concerning the effect of a sentence until after the verdict is rendered.
unsupported for: The court shall pronounce the sentence orally in open court. The court may thereafter issue a written order that shall be consistent with th
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
85611ms · graded 2026-08-28 10:07
25%hll-cl11405924-1healthcare-medmaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: sufficient knowledge, skill, experience, training, or education
unsupported for: Managing Diabetes in Patients Receiving Chronic Steroids.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
91823ms · graded 2026-08-28 10:07
25%hll-cl11405907-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity33%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
supported for: I have no objections … except I just ask that the State remove the stickies from the reports before they go back to the jury room,
unsupported for: A party waives any objection to the admission of evidence if the party fails to timely object at trial, unless the error is plain error that
unsupported for: seriously affects the fairness, integrity, or public reputation of the judicial proceedings.
unsupported for: A party may not be heard on an issue that was not preserved for appeal.
unsupported for: No person shall be compelled … to be a witness against himself.
supported for: I have no objections … except I just ask that the State remove the stickies from the reports before they go back to the jury room.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
106559ms · graded 2026-08-28 10:07
25%hll-cl11406802-1criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: what the community thinks is appropriate
unsupported for: the danger of unfair prejudice is heightened when the evidence is highly inflammatory and only marginally probative.
unsupported for: consider what the community expects of a police officer who abuses his position,
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
45391ms · graded 2026-08-28 10:06
25%hll-cl11405907-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found453 S.W.3d 123 · in CourtListener bulk table
found511 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: An issue is preserved for appellate review only if a timely objection is made and a ruling is entered on the objection.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
96050ms · graded 2026-08-28 10:06
25%hll-cl11405911-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity50%×2
Citation checks
found332 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
no passage332 S.W.3d 1 for: when there is a factual basis to question the defendant’s competency.
no passage332 S.W.3d 1 for: must make a competency determination whenever a factual basis exists
unsupported for: the presence of any indication of mental disorder that could affect the defendant’s ability to understand the proceedings mandates at least
supported for: I live by the Ten Commandments… rebuilding the temple in Israel until the rapture
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
33060ms · graded 2026-08-28 10:05
0%hll-cl11405904-2civil-litigationdifficulty 4private splitblankopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
89524ms · graded 2026-08-28 10:05
25%hll-cl11405905-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: deprive the defendant of a fair trial.
unsupported for: impermissibly disclosed bias, prejudice, or personal information
unsupported for: creates a trial that is fundamentally unfair.
unsupported for: deprives the defendant of a fundamentally fair trial.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
66070ms · graded 2026-08-28 10:05
67%hll-cl11405905-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
76446ms · graded 2026-08-28 10:05
0%hll-cl11405545-3criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found332 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
no passage332 S.W.3d 1 for: A judgment of fine, costs, or restitution shall be pronounced in open court.
unsupported for: state the factual and legal basis for the conclusion that the judgment is void, or that the appeal is without merit, and must also address a
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
95922ms · graded 2026-08-28 10:05
50%hll-cl11405545-4criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found71 S.W.3d 1 · in DocketRouter index
found201 S.W.3d 1 · in CourtListener bulk table
unverified201 S.W.3d 123 · verifier request budget exhausted
unverified200 S.W.3d 456 · verifier request budget exhausted
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
80600ms · graded 2026-08-28 10:05
25%hll-cl11405128-04criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found332 S.W.3d 1 · in CourtListener bulk table
found200 S.W.3d 1 · in CourtListener bulk table
unverified201 S.W.3d 123 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the danger of unfair prejudice… outweighs any minimal probative value
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
169625ms · graded 2026-08-28 10:05
25%hll-cl11405863-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found342 U.S. 1 · in DocketRouter index
in opinion481 U.S. 739
found100 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: All persons shall be bailable… unless the evidence is sufficient to justify a charge of a capital offense… The bail shall be reasonable.
unsupported for: The Eighth Amendment… forbids the setting of bail at an amount higher than is reasonably required.
unsupported for: The government may not set bail at a level that is punitive.
unsupported for: The trial court’s decision is reviewed for abuse of discretion; the appellate court will not substitute its judgment for that of the trial c
unsupported for: normally result in a lower bond unless counter‑balanced by compelling evidence of flight risk.
unsupported for: final as to the rights of the parties
unsupported for: arbitrary, unreasonable, or manifestly contrary to law
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
64046ms · graded 2026-08-28 10:05
25%hll-cl11405530-3criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity50%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
supported for: intentionally and knowingly penetrated … without [B]’s consent
unsupported for: the trial court’s role is limited to determining whether the evidence, when viewed in the light most favorable to the State, is sufficient t
unsupported for: had a substantial and injurious effect or influence on the jury’s verdict.
supported for: intentionally and knowingly penetrated … without [B]’s consent.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
95197ms · graded 2026-08-28 10:04
25%hll-cl11405132-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found442 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: to be present at all material stages of the trial.
unsupported for: shall be present at the trial
no passage442 S.W.3d 1 for: seriously disrupt the orderly conduct of the trial
no passage442 S.W.3d 1 for: pose a threat to the safety of any person.
unsupported for: the error did not affect the substantial rights of the appellant
unsupported for: the appellant cannot show that the error contributed to the verdict.
unsupported for: [A]’s conduct constituted a clear and present danger to courtroom safety and to the orderly conduct of voir dire.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
99654ms · graded 2026-08-28 10:04
25%hll-cl11405542-1divorce-propertydifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: all evidence on which the trial court relied.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
54826ms · graded 2026-08-28 10:04
67%hll-cl11405545-1criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
32605ms · graded 2026-08-28 10:04
25%hll-cl11405129-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority67%×2
Quote fidelity0%×2
Citation checks
in opinion373 U.S. 83
in opinion473 U.S. 667
unverified502 F.2d 1265 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: if the trial cannot be fairly continued
unsupported for: if a serious error has occurred that cannot be cured by a new trial.
unsupported for: material evidence was not presented at trial
unsupported for: so serious that a fair trial cannot be continued
unsupported for: so serious that a fair trial cannot be continued
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
85830ms · graded 2026-08-28 10:04
25%hll-cl11405129-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority63%×2
Quote fidelity0%×2
Citation checks
in opinion373 U.S. 83
in opinion473 U.S. 667
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: favorable to the accused…and material to either guilt or punishment.
unsupported for: any evidence that is material to the defense
unsupported for: any evidence that tends to exonerate the accused.
unsupported for: Alternative‑perpetrator evidence is per se material because it tends to raise a reasonable doubt as to the defendant’s guilt.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
90426ms · graded 2026-08-28 10:04
25%hll-cl11405530-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity80%×2
Citation checks
found361 S.W.3d 1 · in CourtListener bulk table
found201 S.W.3d 1 · in CourtListener bulk table
found247 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
supported for: unconscious or physically unable to resist
supported for: unconscious or physically unable to resist
supported for: [A] intentionally and knowingly penetrated the sexual organ of [B] … without [B]’s consent.
unsupported for: the free and voluntary agreement of the victim to the sexual act.
supported for: unconscious or physically unable to resist
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
52088ms · graded 2026-08-28 10:04
25%hll-cl11405530-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity25%×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
found123 S.W.3d 123 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: knew the complainant was unaware that the sexual assault was occurring
unsupported for: knowledge that the victim is unaware that a sexual assault is occurring
unsupported for: mistaken about the identity of the assailant
supported for: intentionally and knowingly penetrated … without [B]’s consent.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
30665ms · graded 2026-08-28 10:03
25%hll-cl11404091-02criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: exclusive possession of the vehicle is not required; what matters is the defendant’s knowledge and control of the contraband itself.
unsupported for: knowledge of the presence of the drug is a factual issue, but the sufficiency of the State’s evidence on that issue is reviewed de novo.
unsupported for: awareness of the nature of the substance
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
75983ms · graded 2026-08-28 10:03
50%hll-cl11404091-04criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
found201 S.W.3d 1 · in CourtListener bulk table
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
62832ms · graded 2026-08-28 10:03
0%hll-cl11404067-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
unverified414 S.W.3d 351 · verifier rate-limited
found657 S.W.2d 540 · in CourtListener bulk table
unverified808 S.W.2d 784 · verifier rate-limited
unverified559 S.W.3d 377 · verifier rate-limited
unverified187 S.W.3d 408 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
no passage414 S.W.3d 351 for: appointed counsel shall be given at least ten (10) days to prepare for the hearing.
no passage808 S.W.2d 784 for: deprives the defendant of a meaningful opportunity to prepare an effective defense.
no passage808 S.W.2d 784 for: the hearing shall be held at least seven (7) days after service of the motion, unless the parties agree in writing to a shorter period.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
81097ms · graded 2026-08-28 10:03
50%hll-cl11405530-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
unverified503 U.S. 227 · verifier request budget exhausted
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
9342ms · graded 2026-08-28 10:03
25%hll-cl11405129-3criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority63%×2
Quote fidelity0%×2
Citation checks
in opinion373 U.S. 83
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: The State shall disclose to the defense any evidence that is material to the guilt or innocence of the defendant.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
17159ms · graded 2026-08-28 10:03
50%hll-cl11405128-03criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found200 S.W.3d 1 · in CourtListener bulk table
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
33570ms · graded 2026-08-28 10:03
88%hll-cl11404067-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority75%×2
Quote fidelity-×2
Citation checks
found487 U.S. 654 · in DocketRouter index
in opinion411 U.S. 778
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
46048ms · graded 2026-08-28 10:02
22%hll-cl11404064-4criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity67%×2
Citation checks
in opinion386 U.S. 738
found1 S.W.2d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
supported for: a public servant lawfully discharging an official duty
unsupported for: grant the appellant’s Anders brief, appoint counsel, and continue the appeal for briefing on the merits.
supported for: public servant lawfully discharging an official duty,
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
56007ms · graded 2026-08-28 10:02
50%hll-cl11404060-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
in opinion373 U.S. 83
found427 U.S. 97 · in DocketRouter index
in opinion386 U.S. 738
in opinion466 U.S. 668
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
71646ms · graded 2026-08-28 10:02
0%hll-cl11404067-3criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found453 S.W.3d 123 · in CourtListener bulk table
found361 S.W.3d 1 · in CourtListener bulk table
unverified789 S.W.3d 456 · verifier request budget exhausted
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
33557ms · graded 2026-08-28 10:02
33%hll-cl11404058-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard100%×2
Authority0%×2
Quote fidelity-×2
Citation checks
found201 S.W.3d 1 · in CourtListener bulk table
found453 S.W.3d 1 · in DocketRouter index
found299 S.W.3d 1 · in CourtListener bulk table
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
73658ms · graded 2026-08-28 10:02
33%hll-cl11404057-03criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard0%×2
Authority0%×2
Quote fidelity-×2
Citation checks
found201 S.W.3d 1 · in CourtListener bulk table
unverified201 S.W.3d 100 · verifier request budget exhausted
unverified201 S.W.3d 123 · verifier request budget exhausted
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
71737ms · graded 2026-08-28 10:02
25%hll-cl11404058-3criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity50%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
supported for: could possibly reflect an anarchy symbol
unsupported for: gang members…are more inclined to be violent.
supported for: you’re just trying to back‑door the hand tattoo
unsupported for: identify the issues raised on appeal and the relief sought.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
53889ms · graded 2026-08-28 10:02
67%hll-cl11404043-4criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity-×2
Citation checks
found68 S.W.3d 1 · in DocketRouter index
found71 S.W.3d 1 · in DocketRouter index
found84 S.W.3d 1 · in DocketRouter index
found115 S.W.3d 1 · in DocketRouter index
found140 S.W.3d 1 · in DocketRouter index
found162 S.W.3d 1 · in CourtListener bulk table
found176 S.W.3d 1 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
116623ms · graded 2026-08-28 10:02
25%hll-cl11404060-4criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found362 S.W.3d 1 · in CourtListener bulk table
found453 S.W.3d 1 · in DocketRouter index
in opinion466 U.S. 668
in opinion373 U.S. 83
found332 S.W.3d 1 · in CourtListener bulk table
found473 U.S. 667 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: identifies any claim that may be raised on appeal that is not frivolous, meritless, or without a basis in law or fact.
unsupported for: has failed to raise any issue that could reasonably be argued to have merit.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
20007ms · graded 2026-08-28 10:02
67%hll-cl11404042-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity100%×2
Citation checks
found407 U.S. 514 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
supported for: reasonable time to prepare for trial
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
133998ms · graded 2026-08-28 10:02
25%hll-cl11404064-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity25%×2
Citation checks
found382 S.W.3d 1 · in CourtListener bulk table
in opinion386 U.S. 738
found201 S.W.3d 1 · in CourtListener bulk table
unverified201 S.W.3d 456 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: Was the victim a public servant lawfully discharging an official duty at the time of the assault?
supported for: a public servant lawfully discharging an official duty
unsupported for: while the public servant is lawfully discharging an official duty
unsupported for: wearing his uniform, badge, and protective vest.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
8346ms · graded 2026-08-28 10:01
67%hll-cl11404057-04criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity-×2
Citation checks
found949 S.W.2d 1 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
36450ms · graded 2026-08-28 10:01
25%hll-cl11404058-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity13%×2
Citation checks
found949 S.W.2d 1 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: serve only to inflame the jury
unsupported for: the error did not affect the substantial rights of a party
unsupported for: the evidence of record is sufficient to support the verdict beyond a reasonable doubt.
unsupported for: cumulative, harmless, or merely a technical error.
unsupported for: material to an issue in the case
supported for: Let’s be honest… you’re just trying to back‑door the hand tattoo.
unsupported for: the photograph is offered solely to show the presence of a metal ring and the tattoo; you may not consider the tattoo as evidence of the vic
unsupported for: relates to a core issue of the case.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
22681ms · graded 2026-08-28 10:01
50%hll-cl11403606-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
found201 S.W.3d 1 · in CourtListener bulk table
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
159186ms · graded 2026-08-28 10:01
25%hll-cl11404054-02criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found311 S.W.3d 1 · in DocketRouter index
found201 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: The purpose of Rule 608(b) is to prevent the jury from being swayed by character evidence that is not directly relevant to the issues in dis
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
75748ms · graded 2026-08-28 10:01
25%hll-cl11404054-1criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found361 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: had no concerns about the complainant’s veracity
unsupported for: Any party may attack or support the credibility of any witness….
unsupported for: Evidence of a witness’s character for truthfulness or untruthfulness is admissible…through reputation or opinion testimony.
unsupported for: the witness’s demeanor, affect, or credibility
unsupported for: has no concerns about the victim’s veracity,
unsupported for: I have no concerns about the complainant’s veracity
unsupported for: her statements were consistent with her outcry.
unsupported for: I have no concerns about the complainant’s veracity.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
37738ms · graded 2026-08-28 10:01
25%hll-cl11404043-3criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the gaps between indictments and the time spent in Arkansas rendered the remaining incarceration non‑prejudicial
unsupported for: any order disposing of an indictment, information, or complaint
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
73787ms · graded 2026-08-28 10:01
25%hll-cl11404054-04criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
unverified123 S.W.3d 456 · verifier request budget exhausted
found332 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: had no concerns about the victim’s credibility
no passage123 S.W.3d 456 for: he had no concerns about the victim’s statements
unsupported for: had no concerns about B’s veracity
unsupported for: had no concerns to bring to the detective.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
45919ms · graded 2026-08-28 10:01
25%hll-cl11404042-3criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found407 U.S. 514 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the State’s failure to act promptly, absent a showing of purposeful or reckless disregard for the defendant’s rights, does not, by itself, c
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
79213ms · graded 2026-08-28 10:01
25%hll-cl11403610-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
unverified511 U.S. 338 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the existence of a substantial quantity of a controlled substance, coupled with evidence that the defendant possessed the means to sell the
unsupported for: direct evidence of intent to deliver.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
79125ms · graded 2026-08-28 10:00
25%hll-cl11403610-3criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: apartment‑complex management told him drugs were being sold from a specific unit.
unsupported for: exact copies of the records made and kept in the course of regularly conducted activity.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
48501ms · graded 2026-08-28 10:00
0%hll-cl11404042-4criminaldifficulty 4private splitblankopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
14652ms · graded 2026-08-28 10:00
50%hll-cl11403610-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
32701ms · graded 2026-08-28 10:00
25%hll-cl11403606-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: are sufficient to infer intent to deliver.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
70331ms · graded 2026-08-28 10:00
25%hll-cl11402773-02criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: if the error is so prejudicial that a fair trial cannot be had.
unsupported for: If the jury’s exposure to the inadmissible evidence is uncertain, the trial court may elect to give a curative instruction rather than decla
unsupported for: was previously convicted of assaulting his ex‑wife.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
65484ms · graded 2026-08-28 09:59
25%hll-cl11403606-3criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: shall consider the evidence in the light most favorable to the verdict, and shall not consider any evidence that was excluded at trial.
unsupported for: does not consider evidence that was erroneously admitted at trial when reviewing legal sufficiency. The court must base its analysis on the
unsupported for: When the issue is legal sufficiency, the appellate court must disregard any evidence that was not properly admitted, even if the trial court
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
49350ms · graded 2026-08-28 09:59
0%hll-cl11403606-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found351 S.W.3d 1 · in CourtListener bulk table
found200 S.W.3d 1 · in CourtListener bulk table
found201 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: in the light most favorable to the State
unsupported for: must view the evidence in the light most favorable to the State and resolve any conflicts in the evidence in the State’s favor; it does not
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
32365ms · graded 2026-08-28 09:59
25%hll-cl11402763-3criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity50%×2
Citation checks
found332 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: reasonable in light of the evidence.
supported for: with the intent to promote or assist the commission of the offense.
supported for: with the intent to promote or assist the commission of the offense
unsupported for: If a person is a party to a burglary that results in death, must he have aided in the killing or is it automatic?
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
102880ms · graded 2026-08-28 09:59
25%hll-cl11402763-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity25%×2
Citation checks
found453 S.W.3d 123 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: If a party to a burglary which resulted in a death must have aided in the killing, or is liability automatic?
unsupported for: intentionally aids, abets, or encourages the commission of the offense
supported for: with the intent to promote or assist the commission of the offense
unsupported for: If a party to a burglary which resulted in a death must have aided in the killing, or is it automatic?
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
95973ms · graded 2026-08-28 09:59
81%hll-cl11403610-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority63%×2
Quote fidelity-×2
Citation checks
in opinion462 U.S. 213
found468 U.S. 897 · in DocketRouter index
unverified571 F.3d 1155 · verifier rate-limited
found573 U.S. 373 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
6862ms · graded 2026-08-28 09:59
0%hll-cl11402764-3criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: The trial court may, upon motion, modify a judgment after the filing of a notice of appeal… for clerical errors, omissions, or any other rea
unsupported for: If the trial court fails to correct a judgment within the time prescribed by Rule 45.1, the appellate court may, on its own motion or upon r
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
63744ms · graded 2026-08-28 09:59
25%hll-cl11402764-4criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found442 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: If the judgment expressly conditions payment on the defendant’s release, the condition controls the time of payment.
no passage442 S.W.3d 1 for: The clerk shall prepare a bill of costs and serve it on the parties. The bill is a statement of the amount assessed and does not create a ne
no passage442 S.W.3d 1 for: The issuance of a bill of costs does not, by itself, create a new enforceable obligation. The bill is a bookkeeping device; the judgment’s t
unsupported for: A bill of costs does not supersede a judgment that conditions payment on release. The State may not compel payment before release absent a c
unsupported for: accrues at the time of judgment
unsupported for: the right to collect is subject to the judgment’s payment provision.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
36756ms · graded 2026-08-28 09:59
25%hll-cl11402782-1criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found539 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: so high as to be unattainable
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
7713ms · graded 2026-08-28 09:59
83%hll-cl11402764-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority67%×2
Quote fidelity-×2
Citation checks
in opinion466 U.S. 668
found453 S.W.3d 1 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
47250ms · graded 2026-08-28 09:58
17%hll-cl11402763-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity50%×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
found201 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
supported for: If there is evidence that a person is a party to a burglary which resulted in a death, do we have to prove that he aided in the killing or i
no passage453 S.W.3d 1 for: intends to promote or assist the commission of the offense
unsupported for: acted with the intent to promote or assist the commission of the offense
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
65845ms · graded 2026-08-28 09:58
0%hll-cl11402764-1criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: An indictment shall be signed by the foreperson of the grand jury.
unsupported for: Because the statutory requirement is jurisdictional, the trial court lacks authority to proceed when the indictment is not signed by the for
unsupported for: A jurisdictional defect in the indictment is reviewable on appeal even if the defense did not object at trial.
unsupported for: The proper remedy is reversal of the judgment and dismissal of the indictment; the State may re‑indict if it can cure the defect.
unsupported for: The trial court’s failure to recognize a jurisdictional defect constitutes reversible error.
unsupported for: Only the foreperson’s signature satisfies the statutory requirement; the assistant foreperson’s signature is insufficient.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
50462ms · graded 2026-08-28 09:58
33%hll-cl11402741-3criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard0%×2
Authority0%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
116398ms · graded 2026-08-28 09:58
25%hll-cl11402762-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard0%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
found201 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
no passage453 S.W.3d 1 for: If the jury is permitted to rely on unpleaded conduct, the conviction is void unless the error is harmless beyond a reasonable doubt.
no passage201 S.W.3d 1 for: clear, unambiguous, and consistent with the law.
unsupported for: the complainant identified as ‘A.R.’ is not the witness ‘[F]’
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
50539ms · graded 2026-08-28 09:58
25%hll-cl11402758-1healthcare-medmaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority75%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: documents she claimed were expert reports.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
46345ms · graded 2026-08-28 09:58
81%hll-cl11402736-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority63%×2
Quote fidelity-×2
Citation checks
in opinion395 U.S. 752
found392 U.S. 1 · in DocketRouter index
found556 U.S. 332 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
98157ms · graded 2026-08-28 09:58
25%hll-cl11402756-03criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity33%×2
Citation checks
found71 S.W.3d 1 · in DocketRouter index
unverified511 U.S. 342 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: error is harmless if the evidence of guilt is so overwhelming that it could not have produced a different result.
supported for: knowledge, skill, experience, training, or education
unsupported for: the fire started in the front of the house.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
57161ms · graded 2026-08-28 09:58
25%hll-cl11402735-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: *at any time during the period of community supervision, or within 30 days after the expiration of the period of community supervision*.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
99760ms · graded 2026-08-28 09:57
67%hll-cl11402736-3criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity-×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
74201ms · graded 2026-08-28 09:57
25%hll-cl11402758-4healthcare-medmaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority100%×2
Quote fidelity0%×2
Citation checks
found115 S.W.3d 1 · in DocketRouter index
found71 S.W.3d 1 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: if the party requesting the waiver demonstrates that the party is indigent or that the award would cause a hardship.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
8250ms · graded 2026-08-28 09:57
50%hll-cl11402758-2healthcare-medmaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found332 S.W.3d 1 · in CourtListener bulk table
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
12781ms · graded 2026-08-28 09:57
25%hll-cl11402736-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
found427 U.S. 38 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
no passage453 S.W.3d 1 for: Did the officer have probable cause sufficient to justify a safety sweep?
unsupported for: Was there a reasonable belief that evidence would be destroyed?
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
58660ms · graded 2026-08-28 09:57
25%hll-cl11402741-4criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found351 S.W.3d 1 · in CourtListener bulk table
found202 S.W.3d 1 · in CourtListener bulk table
unverified201 S.W.3d 123 · verifier request budget exhausted
found201 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the existence of probable cause to arrest does not, by itself, render a suspect in custody.
unsupported for: we know you were at the scene
unsupported for: Rule 12(b)(3) – Motion to Suppress
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
36081ms · graded 2026-08-28 09:57
50%hll-cl11402735-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
unverified685 S.W.2d 896 · verifier request budget exhausted
unverified825 S.W.2d 59 · verifier request budget exhausted
unverified823 S.W.2d 333 · verifier request budget exhausted
unverified189 S.W.3d 113 · verifier request budget exhausted
unverified52 S.W.3d 504 · verifier request budget exhausted
Quote fidelity (every quotation must exist verbatim in its source)
no passage685 S.W.2d 896 for: the State shall file a petition to adjudicate the defendant not later than the expiration of the period of community supervision.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
88463ms · graded 2026-08-28 09:57
25%hll-cl11402736-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
in opinion395 U.S. 752
found556 U.S. 332 · in DocketRouter index
found520 U.S. 833 · in DocketRouter index
in opinion494 U.S. 325
in opinion563 U.S. 452
found468 U.S. 897 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: areas where a person might be hidden.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
42627ms · graded 2026-08-28 09:57
0%hll-cl11402735-3criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found331 S.W.3d 1 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
49793ms · graded 2026-08-28 09:56
0%hll-cl11402741-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
in opinion384 U.S. 436
found564 U.S. 229 · in DocketRouter index
found468 U.S. 420 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: you are not under arrest and you can leave.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
5583ms · graded 2026-08-28 09:56
25%hll-cl11402734-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: secreting or holding the child in a place where she was not likely to be found
unsupported for: secreted or held the child in a place where she was not likely to be found.
unsupported for: place not likely to be found.
unsupported for: place where the child is not likely to be found
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
56854ms · graded 2026-08-28 09:56
50%hll-cl11402680-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
found468 U.S. 897 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
74801ms · graded 2026-08-28 09:56
25%hll-cl11402680-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found442 S.W.2d 1 · in CourtListener bulk table
unverified2005 Tex. Crim. L. Rev. P. 1 · verifier rate-limited
unverified201 Tex. Crim. L. Rev. P. 1 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the State need not present direct evidence of every element; a series of facts that, taken together, point inexorably to the defendant’s gui
unsupported for: is not per se unreliable; the State bears the burden of showing the witness is trustworthy
unsupported for: has the power to exercise control over the contraband
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
54791ms · graded 2026-08-28 09:56
25%hll-cl11402735-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found361 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the court lacks jurisdiction because the petition was filed after the expiration of community supervision.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
23184ms · graded 2026-08-28 09:56
25%hll-cl11402680-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found352 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the trial court must give a limiting instruction
unsupported for: the absence of such instruction is reversible error.
unsupported for: next to where the device was found.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
45241ms · graded 2026-08-28 09:56
50%hll-cl11402678-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
55250ms · graded 2026-08-28 09:56
50%hll-cl11402680-3criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found442 S.W.3d 1 · in CourtListener bulk table
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
29295ms · graded 2026-08-28 09:56
25%hll-cl11402675-3criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard0%×2
Authority67%×2
Quote fidelity0%×2
Citation checks
in opinion422 U.S. 806
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: so long as the waiver is made knowingly, voluntarily, and intelligently.
unsupported for: if the defendant knowingly and intelligently waives the right to counsel.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
75392ms · graded 2026-08-28 09:56
25%hll-cl11402675-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority63%×2
Quote fidelity0%×2
Citation checks
in opinion466 U.S. 668
found362 U.S. 402 · in DocketRouter index
found539 U.S. 510 · in DocketRouter index
found466 U.S. 648 · in DocketRouter index
found424 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: I am not the person named,
unsupported for: the defendant’s behavior raises a serious doubt as to his competence.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
78293ms · graded 2026-08-28 09:55
25%hll-cl11402669-3criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: grant the State’s motion to dismiss the appeal
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
73346ms · graded 2026-08-28 09:55
25%hll-cl11402678-2criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
found201 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
no passage453 S.W.3d 1 for: The convicting court shall provide the State with a copy of the motion and shall require the State to either deliver the requested evidence
unsupported for: the statutory command is mandatory, not discretionary, and a trial court’s omission defeats the purpose of the DNA‑testing statute.
unsupported for: the error is not harmless even where the evidence sought would not have produced exculpatory results, because the statutory scheme is design
unsupported for: the error did not affect the substantial rights of the parties
unsupported for: the outcome would have been the same without the error.
unsupported for: when a statute imposes a mandatory procedural step, the failure to perform that step is a jurisdictional defect that cannot be cured by a ha
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
27635ms · graded 2026-08-28 09:55
88%hll-cl11402675-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority63%×2
Quote fidelity100%×2
Citation checks
in opinion466 U.S. 668
found362 U.S. 402 · in DocketRouter index
found539 U.S. 510 · in DocketRouter index
in opinion422 U.S. 806
Quote fidelity (every quotation must exist verbatim in its source)
supported422 U.S. 806 for: understood the nature of the proceedings.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
32681ms · graded 2026-08-28 09:55
25%hll-cl11402669-4criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
in opinion386 U.S. 738
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: Findings of fact are reviewed for clear error.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
58531ms · graded 2026-08-28 09:55
50%hll-cl11402678-3criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
6074ms · graded 2026-08-28 09:55
88%hll-cl11402675-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority63%×2
Quote fidelity-×2
Citation checks
in opinion422 U.S. 806
found362 U.S. 402 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
no passage362 U.S. 402 for: *if he knowingly and intelligently* waives the assistance of counsel.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
44748ms · graded 2026-08-28 09:55
0%hll-cl11402678-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found352 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: likely to produce evidence that would be material to the case
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
9026ms · graded 2026-08-28 09:55
25%hll-cl11402666-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
unverified102 S.W.3d 314 · verifier request budget exhausted
unverified86 S.W.2d 77 · verifier request budget exhausted
unverified30 S.W.3d 93 · verifier request budget exhausted
unverified553 S.W.2d 585 · verifier request budget exhausted
found662 S.W.2d 617 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
no passage86 S.W.2d 77 for: The trial court’s findings of fact and the jury’s credibility determinations are presumed correct. An appellate court may not re‑weigh the
no passage553 S.W.2d 585 for: If reasonable minds could differ as to the weight to be given to the testimony, the conviction must stand.
no passage662 S.W.2d 617 for: the evidence, when viewed in the light most favorable to the State, could have produced a verdict of guilt beyond a reasonable doubt.
unsupported for: sole judge of the witnesses’ credibility and the weight to be given to their testimony.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
62587ms · graded 2026-08-28 09:55
0%hll-cl11402669-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found386 U.S. 263 · in DocketRouter index
found201 S.W.3d 1 · in CourtListener bulk table
unverified201 S.W.3d 100 · verifier request budget exhausted
unverified201 S.W.3d 456 · verifier request budget exhausted
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: must independently review the record for any arguable grounds for reversal, even if the appellant failed to preserve the issue at the trial
unsupported for: within the authority of the court.
unsupported for: unreasonable, arbitrary, or not related to the offender’s rehabilitation or public safety.
unsupported for: unrelated to the offender’s rehabilitation or public safety
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
47593ms · graded 2026-08-28 09:55
25%hll-cl11402669-1criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard0%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
unverified386 U.S. 143 · verifier request budget exhausted
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: does not preclude the court from addressing a plain error that affects the judgment.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
48872ms · graded 2026-08-28 09:55
0%hll-cl11402213-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found442 S.W.3d 1 · in CourtListener bulk table
found200 S.W.3d 1 · in CourtListener bulk table
found453 S.W.3d 1 · in DocketRouter index
found382 S.W.3d 1 · in CourtListener bulk table
found466 U.S. 668 · in DocketRouter index
found332 S.W.3d 1 · in CourtListener bulk table
in opinion446 U.S. 335
found417 S.W.3d 1 · in DocketRouter index
found466 U.S. 648 · in DocketRouter index
found470 S.W.3d 1 · in CourtListener bulk table
found511 S.W.3d 1 · in CourtListener bulk table
found350 S.W.3d 1 · in CourtListener bulk table
found540 S.W.3d 1 · in CourtListener bulk table
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
68076ms · graded 2026-08-28 09:54
25%hll-cl11402212-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found466 U.S. 668 · in DocketRouter index
found302 U.S. 319 · in DocketRouter index
unverified476 U.S. 229 · verifier rate-limited
found463 U.S. 277 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: not aware that the State would not provide any consideration for his plea.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
70555ms · graded 2026-08-28 09:54
50%hll-cl11402666-2criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found361 S.W.3d 1 · in CourtListener bulk table
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
40625ms · graded 2026-08-28 09:54
25%hll-cl11402213-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found466 U.S. 668 · in DocketRouter index
found466 U.S. 648 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
no passage466 U.S. 648 for: so severe as to render the trial fundamentally unfair.
unsupported for: no actual conflict because the evidence against A was overwhelming and there was no evidence against C.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
51580ms · graded 2026-08-28 09:54
25%hll-cl11402666-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: must view the evidence in the light most favorable to the State
unsupported for: the trial court’s factual findings, including determinations of credibility, are binding on the appellate court
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
44115ms · graded 2026-08-28 09:54
0%hll-cl11402666-3criminaldifficulty 5private splitblankopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
19081ms · graded 2026-08-28 09:54
50%hll-cl11402212-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found463 U.S. 277 · in DocketRouter index
found501 U.S. 957 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
41996ms · graded 2026-08-28 09:54
25%hll-cl11402212-3criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found442 S.W.3d 1 · in CourtListener bulk table
found332 S.W.3d 1 · in CourtListener bulk table
found511 U.S. 1 · in DocketRouter index
found453 S.W.3d 1 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: When a defendant has not received a plea agreement, the court may impose a cumulative sentence for each offense.
no passage332 S.W.3d 1 for: The judgment shall state the basis for the sentence, including the statutory range, the factors the court considered, and the reasons for th
no passage453 S.W.3d 1 for: No person shall be deprived of life, liberty, or property without due process of law.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
44010ms · graded 2026-08-28 09:54
25%hll-cl11402203-3evidencedifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority67%×2
Quote fidelity0%×2
Citation checks
found361 S.W.3d 1 · in CourtListener bulk table
found201 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: The purpose of the disclosure rule is to prevent surprise and to give the opposing party an opportunity to investigate the exhibits.
unsupported for: Even where a party is not actually surprised, the court may still exclude the exhibit if the late disclosure defeats the purpose of the rule
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
67905ms · graded 2026-08-28 09:54
25%hll-cl11401780-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority63%×2
Quote fidelity0%×2
Citation checks
in opinion466 U.S. 668
found388 U.S. 218 · in DocketRouter index
found466 U.S. 648 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: A reasonable probability… is a probability sufficient to undermine confidence in the outcome.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
122672ms · graded 2026-08-28 09:53
25%hll-cl11402203-1familydifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard0%×2
Authority0%×2
Quote fidelity100%×2
Citation checks
found299 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
supported for: wanted to live as a married couple
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
69466ms · graded 2026-08-28 09:53
33%hll-cl11402203-4familydifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard100%×2
Authority0%×2
Quote fidelity-×2
Citation checks
found201 S.W.3d 1 · in CourtListener bulk table
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
32884ms · graded 2026-08-28 09:53
25%hll-cl11401798-3child-custodydifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity33%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
supported for: Present Circumstances Would Significantly Impair the Child’s Physical Health or Emotional Development
supported for: present circumstances would significantly impair the child’s physical health or emotional development,
unsupported for: does not merely require a preponderance of the evidence; the party must prove the impairment with a higher degree of certainty because the s
unsupported for: requires proof of a significant impairment to the child’s health or emotional development,
unsupported for: requires proof only that the non‑parent would be a better custodian.
unsupported for: person who has a relationship with the child
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
96618ms · graded 2026-08-28 09:53
25%hll-cl11402-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
in opinion397 U.S. 337
found31 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the defendant has a documented history of violent outbursts, is a flight risk, and has threatened courtroom personnel
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
52462ms · graded 2026-08-28 09:53
25%hll-cl11402-3criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found417 S.W.3d 1 · in DocketRouter index
found388 U.S. 218 · in DocketRouter index
found200 S.W.3d 1 · in CourtListener bulk table
found201 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: identified as a condition precedent to its admission
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
51603ms · graded 2026-08-28 09:53
67%hll-cl11402-2criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity100%×2
Citation checks
unverified284 U.S. 145 · verifier request budget exhausted
unverified79 S.W.3d 177 · verifier request budget exhausted
unverified897 S.W.2d 76 · verifier request budget exhausted
found959 S.W.2d 578 · in CourtListener bulk table
unverified830 S.W.2d 124 · verifier request budget exhausted
unverified382 S.W.3d 724 · verifier request budget exhausted
Quote fidelity (every quotation must exist verbatim in its source)
supported for: Injury to a Child by Omission
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
58640ms · graded 2026-08-28 09:53
0%hll-cl11401798-4child-custodydifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard0%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
unverified357 S.W.3d 123 · verifier rate-limited
found200 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
no passage200 S.W.3d 1 for: the question of whether a party has standing is a question of law, but the factual basis for that determination is reviewed for clear error.
unsupported for: the trial court is the trier of fact and its findings are reviewed for clear error.
unsupported for: mixed question of law and fact.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
61614ms · graded 2026-08-28 09:53
50%hll-cl11401778-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
in opinion443 U.S. 307
found440 U.S. 648 · in DocketRouter index
found534 U.S. 266 · in DocketRouter index
found556 U.S. 332 · in DocketRouter index
unverified517 U.S. 171 · verifier request budget exhausted
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
101085ms · graded 2026-08-28 09:52
25%hll-cl11401779-1criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found569 S.W.2d 604 · in DocketRouter index
unverified679 S.W.2d 871 · verifier request budget exhausted
unverified179 S.W.3d 554 · verifier request budget exhausted
unverified385 S.W.3d 714 · verifier request budget exhausted
Quote fidelity (every quotation must exist verbatim in its source)
no passage679 S.W.2d 871 for: a series of acts indicating a purpose to avoid detection or apprehension.
no passage179 S.W.3d 554 for: the trier of fact may infer intent from the circumstances surrounding the flight.
no passage179 S.W.3d 554 for: a defendant’s failure to stop after an officer’s clear signals, coupled with continued high‑speed travel and evasive maneuvers, creates a pr
no passage385 S.W.3d 714 for: the evidence must be such that a rational trier of fact could find guilt beyond a reasonable doubt
unsupported for: knows the officer is a peace officer
unsupported for: demonstrates a purpose to avoid detection or apprehension.
unsupported for: suggests an intent to conceal the vehicle and to thwart the officer’s efforts.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
78504ms · graded 2026-08-28 09:52
0%hll-cl11401778-3criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found392 U.S. 1 · in DocketRouter index
unverified453 S.W.3d 124 · verifier request budget exhausted
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: whether the error contributed to the verdict in a manner that is not harmless beyond a reasonable doubt.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
83817ms · graded 2026-08-28 09:52
25%hll-cl11401780-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority75%×2
Quote fidelity0%×2
Citation checks
in opinion466 U.S. 668
unverified535 U.S. 617 · verifier request budget exhausted
found466 U.S. 648 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the absence of any reasonable probability of a different result
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
37744ms · graded 2026-08-28 09:52
50%hll-cl11401780-3criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
in opinion466 U.S. 668
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
34111ms · graded 2026-08-28 09:52
25%hll-cl11401778-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found361 S.W.3d 123 · in DocketRouter index
found392 U.S. 1 · in DocketRouter index
unverified949 F.2d 1245 · verifier request budget exhausted
found201 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
no passage361 S.W.3d 123 for: An issue not raised to the trial court is waived and is not subject to appellate review, unless the appellate court determines that the erro
no passage361 S.W.3d 123 for: the appellate court reviews factual findings for clear error and legal conclusions de novo
unsupported for: affects the substantial rights of the appellant.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
58321ms · graded 2026-08-28 09:52
25%hll-cl11401780-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority60%×2
Quote fidelity0%×2
Citation checks
in opinion466 U.S. 668
unverified532 U.S. 154 · verifier rate-limited
found466 U.S. 648 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: sufficiently serious to deprive the defendant of a meaningful opportunity to present a defense.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
24192ms · graded 2026-08-28 09:52
33%hll-cl11401772-2criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard100%×2
Authority0%×2
Quote fidelity-×2
Citation checks
unverified307 S.W.3d 123 · verifier request budget exhausted
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
51940ms · graded 2026-08-28 09:51
25%hll-cl11401764-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity33%×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: where the victim is not likely to be found.
supported453 S.W.3d 1 for: secrete or hold … not likely to be found
unsupported for: a place where the victim is not likely to be found
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
63061ms · graded 2026-08-28 09:51
25%hll-cl11401772-4criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: The trial court’s factual findings are binding unless they are clearly erroneous; its discretionary rulings are reviewed for abuse of discre
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
45170ms · graded 2026-08-28 09:51
25%hll-cl11401779-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the evidence must be such that a rational trier of fact could find the element beyond a reasonable doubt
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
9820ms · graded 2026-08-28 09:51
25%hll-cl11401253-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: pay a fee for the purpose of sexual conduct
unsupported for: pay a fee for the purpose of sexual conduct
unsupported for: pay a fee for the purpose of sexual conduct
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
132722ms · graded 2026-08-28 09:51
25%hll-cl11401253-3criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found418 S.W.3d 1 · in CourtListener bulk table
found473 U.S. 667 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: affects the fairness, integrity, or public reputation of the judicial proceedings.
unsupported for: affects the fairness, integrity, or public reputation of the judicial proceedings.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
107735ms · graded 2026-08-28 09:51
25%hll-cl11401358-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the State has not proved the defendant’s guilt beyond a reasonable doubt,
unsupported for: preserved for appellate review by an appeal‑able step, such as an objection, a motion, or a request for a limiting instruction.
unsupported for: A party who fails to object to the admission of evidence waives any claim of error concerning that evidence.
unsupported for: clear, obvious, and affect the defendant’s substantial rights.
unsupported for: the State has not proved the defendant’s guilt beyond a reasonable doubt
unsupported for: motion that determines the admissibility of evidence,
unsupported for: If the defendant has dominion and control of the container or location where the contraband is found, he is deemed to have possessed the con
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
89681ms · graded 2026-08-28 09:51
25%hll-cl11401359-3criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the question is whether, after viewing the evidence in the light most favorable to the State, a reasonable juror could find the essential el
unsupported for: continued for the majority of her childhood
unsupported for: continued for the majority of my childhood
unsupported for: continued for the majority of my childhood
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
37939ms · graded 2026-08-28 09:51
25%hll-cl11401764-04criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the error did not affect the substantial rights of the appellant.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
29915ms · graded 2026-08-28 09:51
25%hll-cl11401772-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: loud noises, suicidal ideation, attempts to fashion weapons, destructive behavior, and refusal to follow staff instructions.
unsupported for: remain at the facility, obey rules, and not voluntarily terminate participation.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
8160ms · graded 2026-08-28 09:51
25%hll-cl11401253-4criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: Judge [C] assessed [A]’s punishment and sentenced him to forty‑five (45) years’ imprisonment.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
83001ms · graded 2026-08-28 09:51
25%hll-cl11401358-3criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
unverified201 S.W.3d 1234 · verifier rate-limited
unverified201 S.W.3d 567 · verifier rate-limited
unverified201 S.W.3d 1122 · verifier rate-limited
unverified201 S.W.3d 987 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: at the time the evidence is offered
unsupported for: A party who fails to object to the admission of evidence at trial waives any claim of error with respect to that evidence, unless the error
unsupported for: waiver must be clear and unmistakable; ambiguous conduct does not constitute waiver.
unsupported for: record as a whole shows an abandonment
unsupported for: we are abandoning the suppression issue
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
63257ms · graded 2026-08-28 09:51
25%hll-cl11401358-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: A party may object to any evidence, testimony, or argument that is inadmissible, irrelevant, or otherwise improper. Failure to timely object
unsupported for: waiver is a question of fact and must be determined from the entire record.
unsupported for: a party’s failure to object, or an express statement of ‘no objection,’ is a waiver of any claim of error concerning that evidence, unless t
unsupported for: the appellate court may not revive a claim that the trial court waived, even if the waiver was inadvertent.
unsupported for: took steps to preserve the issue.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
48291ms · graded 2026-08-28 09:50
13%hll-cl11401359-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome50%×2
Standard0%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found442 S.W.3d 1 · in CourtListener bulk table
found274 S.W.2d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: causing … contact with the defendant’s genitals.
unsupported for: Caused the child to make contact with the defendant’s genitals.
unsupported for: No, he never made me touch him
unsupported for: causing contact with the defendant’s genitals
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
13405ms · graded 2026-08-28 09:50
25%hll-cl11401358-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: immaterial to the legality of the stop,
unsupported for: unusually nervous, had a dry mouth, was shaking, and tried to keep them away from his vehicle.
unsupported for: immaterial to the lawfulness of the detention.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
46903ms · graded 2026-08-28 09:50
0%hll-cl11400697-1real-propertydifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: removes the Statute of Frauds bar because the buyer has manifested an intent to be bound and the seller has relied on that intent.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
83080ms · graded 2026-08-28 09:50
25%hll-cl11400697-4real-propertydifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome50%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
no citations offered
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
54085ms · graded 2026-08-28 09:50
25%hll-cl11401253-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority57%×2
Quote fidelity0%×2
Citation checks
in opinion541 U.S. 36
found547 U.S. 813 · in DocketRouter index
found562 U.S. 344 · in DocketRouter index
unverified484 F.2d 1245 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
no passage484 F.2d 1245 for: the trial court has broad latitude to determine admissibility
unsupported for: made to a police officer in the course of an emergency
unsupported for: to provide context for A’s incriminating statements.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
38135ms · graded 2026-08-28 09:49
0%hll-cl11400381-3criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: The judgment of conviction and sentence of 48 years’ imprisonment is affirmed. The $100 fine is vacated. Court costs and fees are set at $0.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
50752ms · graded 2026-08-28 09:49
17%hll-cl11400697-3real-propertydifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome50%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found202 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: contract for conveyance of an interest in land
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
39033ms · graded 2026-08-28 09:49
25%hll-cl11400380-4tortdifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome50%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found539 S.W.2d 1 · in CourtListener bulk table
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
83498ms · graded 2026-08-28 09:49
21%hll-cl11400381-1criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority63%×2
Quote fidelity0%×2
Citation checks
in opinion386 U.S. 738
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: grant a judgment of dismissal and order a new trial
unsupported for: grant a judgment of dismissal and order the trial court to correct the judgment
unsupported for: order the trial court to correct the judgment
unsupported for: The appeal is dismissed pursuant to Tex. R. App. P. 33.1(a). The judgment of conviction is affirmed. The trial court is directed to correct
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
64869ms · graded 2026-08-28 09:49
25%hll-cl11400378-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority57%×2
Quote fidelity75%×2
Citation checks
in opinion466 U.S. 668
Quote fidelity (every quotation must exist verbatim in its source)
supported for: claim of ineffective assistance of counsel
supported for: an eye for an eye, a life for a life.
supported for: in Islam it says an eye for an eye…
unsupported for: the prejudice prong is not satisfied where the error is not shown to have had a substantial effect on the verdict
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
81100ms · graded 2026-08-28 09:49
0%hll-cl11400381-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found361 S.W.2d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: grant relief on any ground not raised in the brief
unsupported for: raise any issue it deems appropriate.
unsupported for: may grant relief on any ground not raised in the brief.
unsupported for: shall dismiss the appeal and enter a judgment of acquittal,
unsupported for: direct the trial court to correct the judgment of costs
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
32257ms · graded 2026-08-28 09:49
21%hll-cl11400362-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority63%×2
Quote fidelity0%×2
Citation checks
found384 U.S. 436 · in DocketRouter index
found388 U.S. 218 · in DocketRouter index
found200 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the error was harmless beyond a reasonable doubt
unsupported for: If an error is not preserved, the appellate court may consider it if the error is plain and affects substantial rights.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
123073ms · graded 2026-08-28 09:49
0%hll-cl11400381-4criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found437 S.W.2d 1 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: file a brief stating that no reversible error exists
unsupported for: state that no reversible error exists
unsupported for: affirmed and the case is closed
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
8537ms · graded 2026-08-28 09:49
25%hll-cl11400374-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found442 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
no passage442 S.W.3d 1 for: the evidence would permit a rational jury to find the defendant not guilty of the charged offense but guilty of the lesser‑included offense.
unsupported for: hoped every shot would kill him.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
117933ms · graded 2026-08-28 09:49
0%hll-cl11400380-2tortdifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found539 S.W.2d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: The rule is not absolute; it yields where the defendant’s conduct creates a duty that is independent of the contract, such as a duty to exer
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
50640ms · graded 2026-08-28 09:49
0%hll-cl11400374-2criminaldifficulty 3private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found55 S.W.3d 1 · in DocketRouter index
found299 S.W.3d 1 · in CourtListener bulk table
found224 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: sufficient to support a rational finding
unsupported for: If the evidence of intent to kill is strong enough that a reasonable juror could not honestly conclude that the homicide was the result of r
unsupported for: A lesser‑included instruction is improper where the evidence of the higher‑degree crime is so compelling that it precludes a rational jury q
unsupported for: The presence of a motive and a pre‑meditated act generally defeats a manslaughter instruction, absent a showing that the defendant acted und
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
101138ms · graded 2026-08-28 09:49
25%hll-cl11400374-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the existence of a clear, affirmative statement of intent to kill is ordinarily sufficient to defeat a lesser‑included‑offense instruction w
unsupported for: the trial court’s discretion is not abused where the evidence of intent is uncontradicted and the defendant’s own testimony does not create
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
67388ms · graded 2026-08-28 09:48
25%hll-cl11400352-04criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found316 U.S. 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: a series of acts over a period of time
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
114471ms · graded 2026-08-28 09:48
25%hll-cl11400361-4criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
unverified326 S.W.3d 294 · verifier rate-limited
unverified254 S.W.3d 379 · verifier rate-limited
unverified465 S.W.2d 820 · verifier rate-limited
unverified312 S.W.3d 792 · verifier rate-limited
unverified226 S.W.3d 558 · verifier rate-limited
found371 S.W.3d 576 · in DocketRouter index
unverified497 S.W.3d 489 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
no passage465 S.W.2d 820 for: the error did not affect the substantial rights of the parties and a reasonable juror could have found the defendant guilty beyond a reasona
unsupported for: had a substantial and injurious effect
no passage497 S.W.3d 489 for: the same testimony given in a different medium can be more compelling
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
75391ms · graded 2026-08-28 09:48
25%hll-cl11400338-1criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome50%×2
Standard-×2
Authority67%×2
Quote fidelity0%×2
Citation checks
in opinion466 U.S. 668
found453 S.W.3d 1 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: strategic choices, even if unwise, do not constitute deficient performance
unsupported for: the prejudice prong is not satisfied where the omitted testimony is merely cumulative of other evidence
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
129612ms · graded 2026-08-28 09:48
83%hll-cl11400352-02criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority67%×2
Quote fidelity-×2
Citation checks
unverified514 U.S. 400 · verifier request budget exhausted
in opinion284 U.S. 299
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
82220ms · graded 2026-08-28 09:47
25%hll-cl11400374-3criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found299 S.W.3d 1 · in CourtListener bulk table
unverified345 S.W.3d 456 · verifier request budget exhausted
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: whether the trial court’s refusal to give a lesser‑included‑offense instruction was an error of law
unsupported for: the evidence would permit a rational jury to find the defendant guilty of the lesser offense.
unsupported for: evidence of a defendant’s fear or ‘heat of passion’ does not, by itself, create a reasonable doubt as to intent when the defendant expressly
unsupported for: the existence of a voluntary‑manslaughter instruction is proper only where the evidence raises a genuine issue of fact as to whether the kil
unsupported for: unambiguous proof of the higher‑level mental state.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
5331ms · graded 2026-08-28 09:47
25%hll-cl1140029-4criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
unverified473 U.S. 83 · verifier request budget exhausted
found108 S.W.3d 1 · in CourtListener bulk table
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: essential to preserve a substantial interest
no passage473 U.S. 83 for: necessary to protect the victim or a witness.
unsupported for: The trial court must articulate, on the record, the specific interest it seeks to protect, why that interest is substantial, and why the clo
unsupported for: A mere convenience or preference does not satisfy the first factor.
unsupported for: When the witness is not the victim, the State’s interest in protecting the victim is not implicated; the court must identify a separate, sub
unsupported for: A closure order that lacks the requisite findings is a reversible error, even if the closure would otherwise be permissible.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
94450ms · graded 2026-08-28 09:47
25%hll-cl11400282-03criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome0%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found481 U.S. 739 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: upon cash bond, surety bond, property bond, personal recognizance, or personal bond
unsupported for: reasonable in light of the circumstances
unsupported for: shall not be set at an amount that the defendant cannot reasonably pay.
unsupported for: in an amount that is not excessive
unsupported for: grossly disproportionate to the defendant’s ability to pay
unsupported for: the Constitution and Chapter 10 require the trial court to set a bond that is reasonably related to the defendant’s flight risk and danger t
unsupported for: the trial court’s discretion is not unfettered; it is bounded by the statutory requirement that bail be reasonable and that the defendant’s
unsupported for: failed to consider the defendant’s inability to pay and therefore abused its discretion.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
93286ms · graded 2026-08-28 09:47
25%hll-cl11400282-04criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
unverified309 S.W.3d 743 · verifier rate-limited
unverified769 S.W.2d 459 · verifier rate-limited
unverified395 S.W.3d 280 · verifier rate-limited
found295 S.W.3d 504 · in CourtListener bulk table
unverified312 S.W.3d 292 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: Excessive bail shall not be required.
unsupported for: will not reverse a trial‑court decision unless the decision is arbitrary, unreasonable, or an error of law.
unsupported for: Bail may be set at a level that is unlikely to be posted if the court finds a substantial danger to the community.
unsupported for: higher than the amount the defendant can afford
unsupported for: higher than the amount the defendant can reasonably be expected to post
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
76265ms · graded 2026-08-28 09:47
25%hll-cl1140028-3criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: all witnesses, including the victim, be excluded from the courtroom during the guilt phase
unsupported for: the right of the people to a trial by an impartial jury, a public trial, and the right to be informed of the nature and cause of the accusat
unsupported for: the exclusion of the public from the courtroom for the entire duration of the trial.
unsupported for: the public‑trial right is not offended by the exclusion of a *witness* who is not a member of the public.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
87079ms · graded 2026-08-28 09:47
25%hll-cl11400361-3criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found453 S.W.3d 1 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: An error is harmless if the appellate court, after a review of the entire record, is convinced beyond a reasonable doubt that the error did
unsupported for: The State bears the burden of proving that the error was harmless beyond a reasonable doubt.
unsupported for: The appellate court must examine the entire record and consider whether the error was cumulative or merely cumulative prejudice.
unsupported for: If the error is harmless, the conviction is affirmed.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
26917ms · graded 2026-08-28 09:47
52%hll-cl11400278-3criminaldifficulty 5private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard0%×2
Authority57%×2
Quote fidelity-×2
Citation checks
in opinion466 U.S. 668
found469 U.S. 45 · in DocketRouter index
found124 S.W.3d 1 · in CourtListener bulk table
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
92285ms · graded 2026-08-28 09:46
25%hll-cl1140028-02criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard-×2
Authority63%×2
Quote fidelity0%×2
Citation checks
in opinion466 U.S. 668
unverified532 U.S. 154 · verifier request budget exhausted
found466 U.S. 648 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: entirely within the range of professionally competent assistance
unsupported for: the appellate court may not infer ineffective assistance where the trial record is silent as to the reasons for the attorney’s actions
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
63366ms · graded 2026-08-28 09:46
25%hll-cl11400282-02criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard100%×2
Authority0%×2
Quote fidelity0%×2
Citation checks
no citations offered
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: in consideration of the nature and circumstances of the offense, the weight of the evidence, the character and reputation of the defendant,
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
53387ms · graded 2026-08-28 09:46
25%hll-cl11400278-2criminaldifficulty 4private splitopenai/gpt-oss-120b · raw
Axes
Outcome100%×2
Standard0%×2
Authority57%×2
Quote fidelity0%×2
Citation checks
found403 U.S. 602 · in DocketRouter index
found491 U.S. 397 · in DocketRouter index
in opinion466 U.S. 668
found511 U.S. 1 · in DocketRouter index
found507 U.S. 725 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: Islam says ‘eye for an eye’
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
62394ms · graded 2026-08-28 09:46