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
0%hll-cl11405542-1divorce-propertydifficulty 4private splitopenai/gpt-oss-120b · dr2
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found623 S.W.3d 565 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
31805ms · graded 2026-08-28 23:34
25%hll-cl11405542-1divorce-propertydifficulty 4private splitgoogle/gemini-3.7-flash · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
in opinion782 S.W.2d 842
found96 S.W.3d 227 · in DocketRouter index
found960 S.W.2d 613 · in DocketRouter index
in opinion615 S.W.2d 696
found394 S.W.2d 780 · in DocketRouter index
found83 S.W.3d 789 · in DocketRouter index
found526 S.W.3d 471 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported615 S.W.2d 696 for: just and right, having due regard for the rights of each party.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
14113ms · graded 2026-08-28 22:34
50%hll-cl11405542-1divorce-propertydifficulty 4private splitdeepseek/deepseek-v4-flash · dr2
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found623 S.W.3d 565 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
no passage623 S.W.3d 565 for: the filing of the reporter’s record, we cannot address her appellate claims
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
38614ms · graded 2026-08-28 22:36
50%hll-cl11335144-1divorce-propertydifficulty 3private splitgoogle/gemini-3.7-flash · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found641 S.W.2d 210 · in DocketRouter index
found345 S.W.2d 722 · in DocketRouter index
found802 S.W.2d 647 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
18322ms · graded 2026-08-28 21:58
78%hll-cl11081643-3divorce-propertydifficulty 5private splitgoogle/gemini-3.7-flash · dr2
Axes
Outcome100%×2
Standard-×2
Authority56%×2
Quote fidelity-×2
Citation checks
in opinion554 S.W.2d 137
found131 S.W.3d 605 · in DocketRouter index
found615 S.W.2d 696 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
26751ms · graded 2026-08-28 20:20
50%hll-cl11335144-1divorce-propertydifficulty 3private splitopenai/gpt-oss-20b · dr2
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found959 S.W.2d 615 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
109079ms · graded 2026-08-28 20:07
85%hll-cl11081643-3divorce-propertydifficulty 5private splitgoogle/gemini-3.7-flash · raw
Axes
Outcome100%×2
Standard-×2
Authority56%×2
Quote fidelity100%×2
Citation checks
found488 S.W.2d 390 · in DocketRouter index
in opinion554 S.W.2d 137
found641 S.W.2d 210 · in DocketRouter index
found925 S.W.2d 696 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
supported488 S.W.2d 390 for: the recovery for personal injuries sustained by the spouse during marriage, except any recovery for loss of earning capacity during marriage
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
22096ms · graded 2026-08-28 18:55
25%hll-cl11335144-1divorce-propertydifficulty 3private splitopenai/gpt-oss-120b · dr2
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: once a trial court in a Texas divorce proceeding establishes personal jurisdiction over both spouses, it applies Texas law in making its div
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
63610ms · graded 2026-08-28 17:50
50%hll-cl11335144-1divorce-propertydifficulty 3private splitdeepseek/deepseek-v4-flash · dr2
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found143 S.W.3d 237 · in DocketRouter index
found665 S.W.2d 414 · in DocketRouter index
found641 S.W.2d 210 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
23146ms · graded 2026-08-28 16:01
67%hll-cl11335144-1divorce-propertydifficulty 3private splitupstage/solar-pro4 · dr2
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: [O]nce a trial court in a Texas divorce proceeding establishes personal jurisdiction over both spouses, it applies Texas law in making its d
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
67485ms · graded 2026-08-28 15:57
50%hll-cl11081643-3divorce-propertydifficulty 5private splitopenai/gpt-oss-20b · dr2
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found615 S.W.2d 696 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
50765ms · graded 2026-08-28 12:42
0%hll-cl11081643-3divorce-propertydifficulty 5private splitopenai/gpt-oss-120b · dr2
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found832 S.W.2d 194 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
57425ms · graded 2026-08-28 11:59
0%hll-cl11405542-1divorce-propertydifficulty 4private splitblankopenai/gpt-oss-20b · 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.
72676ms · graded 2026-08-28 11:08
0%hll-cl11335144-1divorce-propertydifficulty 3private splitblankopenai/gpt-oss-20b · 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.
57009ms · graded 2026-08-28 10:15
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
0%hll-cl11081643-3divorce-propertydifficulty 5private splitblankopenai/gpt-oss-20b · 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.
4133ms · graded 2026-08-28 09:23
25%hll-cl11335144-1divorce-propertydifficulty 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: the law of the state where the property is situated governs the ownership and disposition of that property.
unsupported for: the law of the state in which real property is located governs its characterization as community or separate property in a divorce proceedin
unsupported for: for real property situated outside Texas, the controlling law is that of the state where the property is located.
unsupported for: constitutes an error of law reviewed de novo.
unsupported for: all property acquired during marriage is community unless proven separate
unsupported for: The trial court erred in applying Texas community‑property law to real property located in Oregon. Under Texas Civ. Prac. & Remedies Code §§
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
93644ms · graded 2026-08-28 09:12
50%hll-cl11405542-1divorce-propertydifficulty 4private splitupstage/solar-pro4 · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found594 S.W.3d 383 · in DocketRouter index
unverified519 S.W.3d 756 · verifier rate-limited
found578 S.W.3d 823 · in CourtListener bulk table
unverified552 S.W.3d 658 · verifier rate-limited
unverified589 S.W.3d 859 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
no passage519 S.W.3d 756 for: The appellant has the burden to present a record that demonstrates the alleged error.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
33268ms · graded 2026-08-28 08:59
50%hll-cl11081643-3divorce-propertydifficulty 5private splitupstage/solar-pro4 · dr2
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
in opinion168 S.W.3d 802
found615 S.W.2d 696 · in DocketRouter index
found131 S.W.3d 605 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
34379ms · graded 2026-08-28 08:42
0%hll-cl11081643-3divorce-propertydifficulty 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.
12740ms · graded 2026-08-28 08:20
25%hll-cl11081643-3divorce-propertydifficulty 5private splitdeepseek/deepseek-v4-flash · dr2
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity50%×2
Citation checks
found131 S.W.3d 605 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
supported131 S.W.3d 605 for: the recovery for personal injuries sustained by the spouse during marriage, except any recovery for loss of earning capacity during marriage
unsupported for: individual causes of action might be separate property
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
52465ms · graded 2026-08-28 08:23
50%hll-cl11405542-1divorce-propertydifficulty 4private splitdeepseek/deepseek-v4-flash · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found890 S.W.2d 821 · in DocketRouter index
in opinion782 S.W.2d 842
found801 S.W.2d 108 · in DocketRouter index
found932 S.W.2d 29 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
34934ms · graded 2026-08-28 08:03
25%hll-cl11335144-1divorce-propertydifficulty 3private splitupstage/solar-pro4 · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity50%×2
Citation checks
unverified282 S.W.3d 565 · verifier request budget exhausted
unverified957 S.W.2d 809 · verifier request budget exhausted
found836 S.W.2d 145 · in DocketRouter index
found975 S.W.2d 584 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: the law of the state where the land is situated determines whether an interest in land is vested.
supported836 S.W.2d 145 for: in a decree of divorce or annulment, the court shall order a division of the estate of the parties in a manner that the court deems just and
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
57131ms · graded 2026-08-28 07:57
0%hll-cl11335144-1divorce-propertydifficulty 3private splitdeepseek/deepseek-v4-flash · raw
Axes
Outcome0%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found641 S.W.2d 210 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
34868ms · graded 2026-08-28 07:27
25%hll-cl11081643-3divorce-propertydifficulty 5private splitupstage/solar-pro4 · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
found665 S.W.2d 107 · in DocketRouter index
unverified201 S.W.3d 348 · verifier request budget exhausted
found836 S.W.2d 145 · in DocketRouter index
unverified202 S.W.3d 112 · verifier request budget exhausted
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: previously indicated that individual causes of action might be separate property.
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
38044ms · graded 2026-08-28 06:49
25%hll-cl11081643-3divorce-propertydifficulty 5private splitdeepseek/deepseek-v4-flash · raw
Axes
Outcome100%×2
Standard-×2
Authority56%×2
Quote fidelity0%×2
Citation checks
found488 S.W.2d 816 · in DocketRouter index
in opinion855 S.W.2d 619
found890 S.W.2d 821 · in DocketRouter index
unverified704 S.W.2d 138 · verifier rate-limited
Quote fidelity (every quotation must exist verbatim in its source)
no passage488 S.W.2d 816 for: property acquired as a result of a personal injury judgment or settlement
unsupported for: individual causes of action might be separate property
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
26032ms · graded 2026-08-28 06:44
25%hll-flp11278367-6divorce-propertydifficulty 4private splitdeepseek/deepseek-v4-flash · dr2
Axes
Outcome50%×2
Standard-×2
Authority0%×2
Quote fidelity33%×2
Citation checks
unverified578 S.W.3d 699 · search unavailable
found255 S.W. 980 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
supported578 S.W.3d 699 for: [W]hen an appellate court remands a case with specific instructions, the trial court is limited to complying with the instructions and canno
no passage255 S.W. 980 for: carry into effect the mandate of the appellate court according to its true intent and meaning
unsupported for: remanded for a new sufficiency analysis.
unsupported for: whether the statements support [C]’s assumptions and whether the trial court would find his testimony less credible were not matters the cou
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
65727ms · graded 2026-08-27 21:27
83%hll-flp11278367-3divorce-propertydifficulty 5private splitdeepseek/deepseek-v4-flash · dr2
Axes
Outcome100%×2
Standard-×2
Authority67%×2
Quote fidelity-×2
Citation checks
found274 S.W.3d 878 · in DocketRouter index
in opinion168 S.W.3d 802
found164 S.W.3d 607 · in DocketRouter index
in opinion96 S.W.3d 256
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
20614ms · graded 2026-08-27 21:26
71%hll-flp11278367-2divorce-propertydifficulty 4private splitdeepseek/deepseek-v4-flash · dr2
Axes
Outcome50%×2
Standard100%×2
Authority63%×2
Quote fidelity-×2
Citation checks
in opinion96 S.W.3d 256
found89 S.W.3d 17 · in DocketRouter index
found131 S.W.3d 605 · in DocketRouter index
found544 S.W.2d 367 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
29287ms · graded 2026-08-27 21:26
87%hll-flp11278367-1divorce-propertydifficulty 4private splitdeepseek/deepseek-v4-flash · dr2
Axes
Outcome100%×2
Standard100%×2
Authority60%×2
Quote fidelity-×2
Citation checks
in opinion168 S.W.3d 802
found46 S.W.3d 237 · in DocketRouter index
found722 S.W.2d 694 · in DocketRouter index
unverified687 S.W.3d 340 · search unavailable
found394 S.W.2d 780 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
23429ms · graded 2026-08-27 21:26
25%hll-flp11278367-3divorce-propertydifficulty 5private splitdeepseek/deepseek-v4-flash · raw
Axes
Outcome100%×2
Standard-×2
Authority67%×2
Quote fidelity0%×2
Citation checks
in opinion168 S.W.3d 802
in opinion96 S.W.3d 256
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: whether the statements support [C]’s assumptions and whether the trial court would find his testimony less credible were not matters the cou
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
112924ms · graded 2026-08-27 19:11
25%hll-flp11278367-1divorce-propertydifficulty 4private splitdeepseek/deepseek-v4-flash · raw
Axes
Outcome100%×2
Standard100%×2
Authority70%×2
Quote fidelity50%×2
Citation checks
found588 S.W.2d 569 · in DocketRouter index
found46 S.W.3d 237 · in DocketRouter index
found715 S.W.2d 629 · in DocketRouter index
in opinion96 S.W.3d 256
unverified496 S.W.3d 195 · search unavailable
in opinion168 S.W.3d 802
Quote fidelity (every quotation must exist verbatim in its source)
supported588 S.W.2d 569 for: that measure or degree of proof which will produce in the mind of the trier of fact a firm belief or conviction as to the truth of the alleg
unsupported for: whether the statements support [C]’s assumptions and whether the trial court would find his testimony less credible were not matters the cou
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
59596ms · graded 2026-08-27 19:10
25%hll-flp11278367-6divorce-propertydifficulty 4private splitdeepseek/deepseek-v4-flash · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity0%×2
Citation checks
in opinion168 S.W.3d 802
found709 S.W.2d 175 · in DocketRouter index
found711 S.W.2d 628 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: remanded for a new sufficiency analysis.
unsupported for: whether the statements support [C]’s assumptions and whether the trial court would find his testimony less credible were not matters the cou
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
22880ms · graded 2026-08-27 19:10
25%hll-flp11278367-2divorce-propertydifficulty 4private splitdeepseek/deepseek-v4-flash · raw
Axes
Outcome100%×2
Standard100%×2
Authority63%×2
Quote fidelity0%×2
Citation checks
in opinion96 S.W.3d 256
found89 S.W.3d 17 · in DocketRouter index
Quote fidelity (every quotation must exist verbatim in its source)
unsupported for: whether the statements support [C]’s assumptions and whether the trial court would find his testimony less credible were not matters the cou
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
42289ms · graded 2026-08-27 19:10
50%hll-cl11405542-3divorce-propertydifficulty 4private splitdeepseek/deepseek-v4-flash · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
found96 S.W.3d 227 · in DocketRouter index
in opinion782 S.W.2d 842
found557 S.W.3d 99 · in DocketRouter index
found338 S.W.3d 59 · in DocketRouter index
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
17165ms · graded 2026-08-27 16:20
50%hll-cl11405542-2divorce-propertydifficulty 4private splitdeepseek/deepseek-v4-flash · raw
Axes
Outcome100%×2
Standard-×2
Authority0%×2
Quote fidelity-×2
Citation checks
in opinion782 S.W.2d 842
found6 S.W.3d 643 · in DocketRouter index
found801 S.W.2d 108 · in DocketRouter index
in opinion615 S.W.2d 696
Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.
17558ms · graded 2026-08-27 16:20