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 runs deepseek/deepseek-v4-flash · raw deepseek/deepseek-v4-flash · juiced deepseek/deepseek-v4-flash · dr2 upstage/solar-pro4 · raw upstage/solar-pro4 · dr2 openai/gpt-oss-120b · raw openai/gpt-oss-20b · raw openai/gpt-oss-120b · dr2 openai/gpt-oss-20b · dr2 google/gemini-3.7-flash · raw google/gemini-3.7-flash · dr2

administrative appellate-mandamus appellate-procedure arbitration assault-iied auto-accident auto-insurance-uim child-custody child-support civil-litigation constitutional construction consumer-dtpa contracts conversion cps-termination criminal defamation discovery divorce-property easements-boundaries elections eminent-domain employment eviction evidence family foreclosure fraud government-municipal groundwater habeas healthcare-medmal hoa-condo homicide ineffective-assistance insurance jurisdiction-trap labor landlord-tenant legal-malpractice limitations nuisance-trespass oil-gas open-records other personal-injury premises-liability probate products-liability professional-responsibility real-estate-brokers real-property school-law search-seizure sovereign-immunity summary-judgment tax theft-fraud-crimes tort tortious-interference trucking venue-forum workers-comp wrongful-death

63%hll-cl11264209-4wrongful-deathdifficulty 5private splitgoogle/gemini-3.7-flash · dr2

Axes

Outcome50%×2

Standard-×2

Authority75%×2

Quote fidelity-×2

Citation checks

found128 S.W.3d 223 · in DocketRouter index

in opinion279 S.W.3d 640

found289 S.W.3d 827 · in DocketRouter index

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

23391ms · graded 2026-08-28 23:15

25%hll-cl11264209-3wrongful-deathdifficulty 4private splitgoogle/gemini-3.7-flash · dr2

Axes

Outcome50%×2

Standard-×2

Authority60%×2

Quote fidelity33%×2

Citation checks

found128 S.W.3d 223 · in DocketRouter index

in opinion279 S.W.3d 640

in opinion52 S.W.3d 749

found842 S.W.2d 266 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

unsupported for: any and all claims, controversies, breaches or disputes

unsupported279 S.W.3d 640 for: arising out of or relating to

supported for: arising out of or related to

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

32715ms · graded 2026-08-28 23:15

88%hll-cl11264209-2wrongful-deathdifficulty 5private splitgoogle/gemini-3.7-flash · dr2

Axes

Outcome100%×2

Standard-×2

Authority75%×2

Quote fidelity-×2

Citation checks

found128 S.W.3d 223 · in DocketRouter index

found517 U.S. 681 · in DocketRouter index

in opinion173 S.W.3d 67

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

25079ms · graded 2026-08-28 23:14

54%hll-cl11264209-1wrongful-deathdifficulty 4private splitgoogle/gemini-3.7-flash · dr2

Axes

Outcome50%×2

Standard-×2

Authority58%×2

Quote fidelity-×2

Citation checks

found128 S.W.3d 223 · in DocketRouter index

in opinion279 S.W.3d 640

in opinion180 S.W.3d 127

found842 S.W.2d 266 · in DocketRouter index

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

26729ms · graded 2026-08-28 23:14

17%hll-cl11264209-3wrongful-deathdifficulty 4private splitgoogle/gemini-3.7-flash · raw

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity0%×2

Citation checks

unverified209 S.W.3d 648 · verifier request budget exhausted

found85 S.W.3d 171 · in DocketRouter index

found420 S.W.3d 81 · in DocketRouter index

found196 S.W.3d 774 · in DocketRouter index

in opinion279 S.W.3d 640

Quote fidelity (every quotation must exist verbatim in its source)

unsupported for: arising out of or relating to the agreement, the property, or the community—encompasses wrongful death and survival claims arising from a f

no passage209 S.W.3d 648 for: are interpreted expansively and create a strong presumption in favor of arbitrability. *See, e.g.*, *In re Prima Title Co.*, 209 S.W.3d 648

unsupported for: The fatal exposure occurred at the gated community's recreation center/pool/spa, and the negligence claims center directly on the appellant

unsupported for: does not remove the claims from an expansive clause that includes

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

26779ms · graded 2026-08-28 21:26

63%hll-cl11264209-4wrongful-deathdifficulty 5private splitgoogle/gemini-3.7-flash · raw

Axes

Outcome50%×2

Standard-×2

Authority75%×2

Quote fidelity-×2

Citation checks

in opinion279 S.W.3d 640

found298 S.W.3d 629 · in DocketRouter index

found672 S.W.3d 367 · in DocketRouter index

found128 S.W.3d 223 · in DocketRouter index

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

18388ms · graded 2026-08-28 21:26

25%hll-cl11264209-2wrongful-deathdifficulty 5private splitgoogle/gemini-3.7-flash · raw

Axes

Outcome50%×2

Standard-×2

Authority75%×2

Quote fidelity0%×2

Citation checks

found517 U.S. 681 · in DocketRouter index

found482 U.S. 483 · in DocketRouter index

in opinion173 S.W.3d 67

found328 S.W.3d 883 · in DocketRouter index

in opinion279 S.W.3d 640

found9 U.S.C. Section 16 · in DocketRouter index

found128 S.W.3d 223 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

unsupported for: shall be valid, irrevocable, and enforceable, save upon such grounds as exist at law or in equity for the revocation of any contract.

no passage328 S.W.3d 883 for: Because the FAA preempts section 171.002(c), the trial court abused its discretion in refusing to compel arbitration based on the lack of an

no passage9 U.S.C. Section 16 for: under the same circumstances that an appeal from a federal district court’s order or decision would be permitted by 9 U.S.C. Section 16.

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

24432ms · graded 2026-08-28 21:26

25%hll-cl11264209-1wrongful-deathdifficulty 4private splitgoogle/gemini-3.7-flash · raw

Axes

Outcome50%×2

Standard-×2

Authority67%×2

Quote fidelity0%×2

Citation checks

found334 S.W.3d 220 · in DocketRouter index

found128 S.W.3d 223 · in DocketRouter index

in opinion279 S.W.3d 640

in opinion52 S.W.3d 749

Quote fidelity (every quotation must exist verbatim in its source)

unsupported52 S.W.3d 749 for: any and all claims arising out of or related to

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

26488ms · graded 2026-08-28 21:25

50%hll-cl11117870-4wrongful-deathdifficulty 4private splitgoogle/gemini-3.7-flash · dr2

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found46 S.W.3d 873 · in DocketRouter index

found701 S.W.2d 238 · in DocketRouter index

found79 S.W.3d 48 · in DocketRouter index

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

37010ms · graded 2026-08-28 20:44

50%hll-cl11117870-1wrongful-deathdifficulty 4private splitgoogle/gemini-3.7-flash · dr2

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.

23212ms · graded 2026-08-28 20:44

25%hll-cl11117870-4wrongful-deathdifficulty 4private splitgoogle/gemini-3.7-flash · raw

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity0%×2

Citation checks

found346 S.W.3d 546 · in DocketRouter index

found274 S.W.3d 681 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

unsupported for: shall enter an order dismissing the claim with prejudice.

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

18692ms · graded 2026-08-28 18:58

25%hll-cl11117870-1wrongful-deathdifficulty 4private splitgoogle/gemini-3.7-flash · raw

Axes

Outcome50%×2

Standard-×2

Authority63%×2

Quote fidelity0%×2

Citation checks

found79 S.W.3d 48 · in DocketRouter index

found46 S.W.3d 873 · in DocketRouter index

unverified332 S.W.3d 524 · verifier request budget exhausted

found439 S.W.3d 332 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

unsupported for: [A] factual and scientific basis for the assertion that the defendant’s failure to act caused the individual to contract the disease.

unsupported for: denies all or part of the relief sought by a motion under Section 148.003(e).

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

24433ms · graded 2026-08-28 18:57

25%hll-cl11264209-4wrongful-deathdifficulty 5private splitopenai/gpt-oss-20b · dr2

Axes

Outcome50%×2

Standard-×2

Authority75%×2

Quote fidelity0%×2

Citation checks

found289 S.W.3d 827 · in DocketRouter index

in opinion279 S.W.3d 640

Quote fidelity (every quotation must exist verbatim in its source)

unsupported for: any and all claims arising out of or related to the purchase agreement, the property, or the community

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

36723ms · graded 2026-08-28 16:36

0%hll-cl11264209-3wrongful-deathdifficulty 4private splitblankopenai/gpt-oss-20b · dr2

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.

47046ms · graded 2026-08-28 16:36

25%hll-cl11264209-2wrongful-deathdifficulty 5private splitopenai/gpt-oss-20b · dr2

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found842 S.W.2d 266 · in DocketRouter index

found328 S.W.3d 883 · in DocketRouter index

found550 U.S. 398 · in CourtListener bulk table

found517 U.S. 681 · in DocketRouter index

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

43454ms · graded 2026-08-28 16:35

17%hll-cl11264209-1wrongful-deathdifficulty 4private splitopenai/gpt-oss-20b · dr2

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity0%×2

Citation checks

found128 S.W.3d 223 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

no passage128 S.W.3d 223 for: any and all claims arising out of or related to the purchase agreement, the property, or the community

unsupported for: any and all claims arising out of or related to the purchase agreement, the property, or the community.

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

70237ms · graded 2026-08-28 16:34

0%hll-cl11264209-4wrongful-deathdifficulty 5private splitopenai/gpt-oss-120b · dr2

Axes

Outcome0%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found289 S.W.3d 827 · in DocketRouter index

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

43479ms · graded 2026-08-28 15:16

70%hll-cl11264209-3wrongful-deathdifficulty 4private splitopenai/gpt-oss-120b · dr2

Axes

Outcome50%×2

Standard-×2

Authority60%×2

Quote fidelity100%×2

Citation checks

in opinion909 S.W.2d 896

found268 S.W.3d 51 · in DocketRouter index

found128 S.W.3d 223 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

supported for: any and all claims…arising out of or related to

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

29086ms · graded 2026-08-28 15:16

50%hll-cl11264209-2wrongful-deathdifficulty 5private splitopenai/gpt-oss-120b · dr2

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found563 U.S. 333 · in DocketRouter index

found409 S.W.3d 91 · in DocketRouter index

found600 S.W.3d 381 · in DocketRouter index

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

49877ms · graded 2026-08-28 15:15

25%hll-cl11264209-1wrongful-deathdifficulty 4private splitopenai/gpt-oss-120b · dr2

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found563 U.S. 333 · in DocketRouter index

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

63018ms · graded 2026-08-28 15:14

25%hll-cl11117870-4wrongful-deathdifficulty 4private splitopenai/gpt-oss-20b · dr2

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found46 S.W.3d 873 · in DocketRouter index

found827 S.W.2d 833 · in DocketRouter index

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

79038ms · graded 2026-08-28 13:26

56%hll-cl11117870-1wrongful-deathdifficulty 4private splitopenai/gpt-oss-20b · dr2

Axes

Outcome50%×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.

26129ms · graded 2026-08-28 13:25

25%hll-cl11264209-4wrongful-deathdifficulty 5private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome50%×2

Standard-×2

Authority75%×2

Quote fidelity0%×2

Citation checks

found289 S.W.3d 827 · in DocketRouter index

in opinion279 S.W.3d 640

found556 U.S. 624 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

unsupported279 S.W.3d 640 for: stands in the shoes of the decedent

unsupported for: a wrongful death beneficiary stands in the shoes of the decedent and is bound by the decedent’s arbitration agreement.

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

27573ms · graded 2026-08-28 13:05

25%hll-cl11264209-3wrongful-deathdifficulty 4private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity57%×2

Citation checks

found128 S.W.3d 223 · in DocketRouter index

found196 S.W.3d 774 · in DocketRouter index

found842 S.W.2d 266 · in DocketRouter index

in opinion180 S.W.3d 127

Quote fidelity (every quotation must exist verbatim in its source)

supported196 S.W.3d 774 for: any dispute . . . arising out of or related to

supported842 S.W.2d 266 for: any suit . . . arising out of or relating to

no passage842 S.W.2d 266 for: that relate to the subject matter of the contract and the parties’ relationship.

unsupported180 S.W.3d 127 for: any doubts concerning the scope of arbitrable issues

unsupported180 S.W.3d 127 for: any claim . . . arising out of or relating to the sale of the Property

supported180 S.W.3d 127 for: [a]ny and all claims, controversies, breaches or disputes

supported for: aris[e] out of or relate[] to

unsupported for: arising out of or relating to

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

46583ms · graded 2026-08-28 13:05

25%hll-cl11264209-2wrongful-deathdifficulty 5private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity80%×2

Citation checks

found128 S.W.3d 223 · in DocketRouter index

found80 S.W.3d 566 · in DocketRouter index

found563 U.S. 333 · in DocketRouter index

found489 U.S. 468 · in DocketRouter index

found416 S.W.3d 168 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

supported563 U.S. 333 for: shall be valid, irrevocable, and enforceable, save upon such grounds as exist at law or in equity for the revocation of any contract.

no passage563 U.S. 333 for: stand as an obstacle to the accomplishment and execution of the full purposes and objectives of Congress.

no passage489 U.S. 468 for: singles out arbitration agreements for disfavored treatment

supported489 U.S. 468 for: each party to the claim, on the advice of counsel, agrees in writing to arbitrate

supported for: signed by each party and each party’s attorney.

supported416 S.W.3d 168 for: the FAA preempts the TAA provision requiring both parties to sign an agreement to arbitrate a personal injury claim because such a provision

unsupported for: interferes with fundamental attributes of arbitration

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

89003ms · graded 2026-08-28 13:04

54%hll-cl11264209-1wrongful-deathdifficulty 4private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome50%×2

Standard-×2

Authority58%×2

Quote fidelity-×2

Citation checks

found128 S.W.3d 223 · in DocketRouter index

found514 U.S. 938 · in DocketRouter index

in opinion180 S.W.3d 127

in opinion279 S.W.3d 640

found563 U.S. 333 · in DocketRouter index

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

58364ms · graded 2026-08-28 13:02

0%hll-cl11117870-4wrongful-deathdifficulty 4private splitopenai/gpt-oss-120b · dr2

Axes

Outcome0%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found262 S.W.3d 316 · in DocketRouter index

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

47235ms · graded 2026-08-28 12:34

21%hll-cl11117870-1wrongful-deathdifficulty 4private splitopenai/gpt-oss-120b · dr2

Axes

Outcome0%×2

Standard-×2

Authority63%×2

Quote fidelity0%×2

Citation checks

no citations offered

Quote fidelity (every quotation must exist verbatim in its source)

unsupported for: provide a factual and scientific basis for the assertion that the defendant’s failure to act caused the individual to contract a pandemic di

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

106149ms · graded 2026-08-28 12:33

25%hll-cl11264209-4wrongful-deathdifficulty 5private splitupstage/solar-pro4 · dr2

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found168 S.W.3d 802 · in DocketRouter index

found842 S.W.2d 266 · in DocketRouter index

found289 S.W.3d 827 · in DocketRouter index

found128 S.W.3d 223 · in DocketRouter index

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

49711ms · graded 2026-08-28 12:14

50%hll-cl11264209-3wrongful-deathdifficulty 4private splitupstage/solar-pro4 · dr2

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity100%×2

Citation checks

found842 S.W.2d 266 · in DocketRouter index

found128 S.W.3d 223 · in DocketRouter index

found514 U.S. 938 · in DocketRouter index

found473 U.S. 614 · in DocketRouter index

found561 U.S. 63 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

supported for: any and all claims … arising out of or related to

supported514 U.S. 938 for: valid, irrevocable, and enforceable, save upon such grounds as exist at law or in equity for the revocation of any contract,

supported for: [a]ny and all claims, controversies, breaches or disputes

supported for: arising out of or related to

supported561 U.S. 63 for: [a]ny and all claims, controversies, breaches or disputes

supported561 U.S. 63 for: arising out of or related to

supported for: claims … arising out of or related to

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

48232ms · graded 2026-08-28 12:13

63%hll-cl11264209-2wrongful-deathdifficulty 5private splitupstage/solar-pro4 · dr2

Axes

Outcome50%×2

Standard-×2

Authority75%×2

Quote fidelity-×2

Citation checks

found128 S.W.3d 223 · in DocketRouter index

found842 S.W.2d 266 · in DocketRouter index

found489 U.S. 468 · in DocketRouter index

found561 U.S. 287 · in DocketRouter index

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

43816ms · graded 2026-08-28 12:12

54%hll-cl11264209-1wrongful-deathdifficulty 4private splitupstage/solar-pro4 · dr2

Axes

Outcome50%×2

Standard-×2

Authority58%×2

Quote fidelity-×2

Citation checks

found563 U.S. 333 · in DocketRouter index

found128 S.W.3d 223 · in DocketRouter index

found842 S.W.2d 266 · in DocketRouter index

in opinion52 S.W.3d 749

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

87346ms · graded 2026-08-28 12:11

0%hll-cl11264209-4wrongful-deathdifficulty 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.

52191ms · graded 2026-08-28 09:48

0%hll-cl11264209-1wrongful-deathdifficulty 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.

59016ms · graded 2026-08-28 09:48

0%hll-cl11264209-3wrongful-deathdifficulty 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.

50108ms · graded 2026-08-28 09:48

25%hll-cl11264209-2wrongful-deathdifficulty 5private splitopenai/gpt-oss-20b · 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.

4193ms · graded 2026-08-28 09:48

67%hll-cl11117870-4wrongful-deathdifficulty 4private splitupstage/solar-pro4 · dr2

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity100%×2

Citation checks

found46 S.W.3d 873 · in DocketRouter index

found827 S.W.2d 833 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

supported827 S.W.2d 833 for: does not represent an objective, good faith effort to provide a factual and scientific basis for the assertion that the defendant’s failure

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

41591ms · graded 2026-08-28 09:20

0%hll-cl11117870-1wrongful-deathdifficulty 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.

43332ms · graded 2026-08-28 09:29

0%hll-cl11117870-4wrongful-deathdifficulty 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.

33561ms · graded 2026-08-28 09:29

50%hll-cl11117870-1wrongful-deathdifficulty 4private splitupstage/solar-pro4 · dr2

Axes

Outcome50%×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: a report authored by at least one qualified expert that provides a factual and scientific basis for the assertion that the defendant’s failu

supported for: does not represent an objective, good faith effort to provide a factual and scientific basis for the assertion that the defendant’s failure

supported for: an objective, good-faith effort to explain—in a nonconclusory fashion—a factual and scientific basis for the assertion that the defendant’s

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

67190ms · graded 2026-08-28 09:19

50%hll-cl11117870-4wrongful-deathdifficulty 4private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found46 S.W.3d 873 · in DocketRouter index

found701 S.W.2d 238 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

no passage701 S.W.2d 238 for: that provides a factual and scientific basis for the assertion that the defendant’s failure to act caused the injured individual to contract

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

41229ms · graded 2026-08-28 08:53

71%hll-cl11117870-1wrongful-deathdifficulty 4private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome50%×2

Standard-×2

Authority63%×2

Quote fidelity100%×2

Citation checks

no citations offered

Quote fidelity (every quotation must exist verbatim in its source)

supported for: a report authored by at least one qualified expert that provides a factual and scientific basis for the assertion that the defendant’s failu

supported for: whether the expert made an objective, good-faith effort to explain—in a nonconclusory fashion—a factual and scientific basis for the asserti

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

50066ms · graded 2026-08-28 08:52

0%hll-cl11264209-1wrongful-deathdifficulty 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.

180005ms · graded 2026-08-28 08:43

25%hll-cl11264209-3wrongful-deathdifficulty 4private splitopenai/gpt-oss-120b · raw

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity25%×2

Citation checks

found563 U.S. 333 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

unsupported for: any and all claims … arising out of or related to the purchase agreement, the property, or the community

unsupported for: any dispute arising out of or relating to

unsupported for: any claim arising out of or relating to the deed

unsupported for: any and all claims … related to the property

supported for: any claim … related to the community

unsupported for: agree that any and all claims … arising out of or related to the purchase agreement, the property, or the community

supported for: any claim … arising out of or related to

unsupported for: any claim … related to the property

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

95612ms · graded 2026-08-28 08:42

17%hll-cl11264209-4wrongful-deathdifficulty 5private splitopenai/gpt-oss-120b · raw

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity0%×2

Citation checks

found563 U.S. 333 · in DocketRouter index

found570 U.S. 228 · in DocketRouter index

found357 S.W.3d 124 · in DocketRouter index

found201 S.W.3d 1 · in CourtListener bulk table

Quote fidelity (every quotation must exist verbatim in its source)

unsupported for: any and all claims arising out of or related to the purchase agreement, the property, or the community

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

64621ms · graded 2026-08-28 08:41

17%hll-cl11264209-2wrongful-deathdifficulty 5private splitopenai/gpt-oss-120b · raw

Axes

Outcome0%×2

Standard-×2

Authority0%×2

Quote fidelity50%×2

Citation checks

found563 U.S. 333 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

supported for: governed by the Federal Arbitration Act.

unsupported for: places any additional procedural or substantive requirements on the parties’ agreement to arbitrate.

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

78581ms · graded 2026-08-28 08:41

17%hll-cl11117870-1wrongful-deathdifficulty 4private splitopenai/gpt-oss-120b · raw

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity0%×2

Citation checks

unverified412 S.W.3d 108 · verifier rate-limited

unverified234 S.W.3d 653 · verifier rate-limited

unverified293 S.W.3d 884 · verifier rate-limited

Quote fidelity (every quotation must exist verbatim in its source)

unsupported for: A plaintiff asserting a claim that a defendant’s failure to act caused a plaintiff to contract a pandemic disease shall, no later than 30 da

unsupported for: If the expert report is deficient, the court shall give the plaintiff an opportunity to cure the deficiency. If the defect is not cured, the

unsupported for: based upon facts or data and reliable principles and methods.

unsupported for: failed to provide masks, plexiglass barriers, and adequate ventilation,

unsupported for: to the best of my knowledge.

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

68313ms · graded 2026-08-28 08:23

17%hll-cl11117870-4wrongful-deathdifficulty 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: shall be subject to dismissal of the claim.

unsupported for: does not establish a scientifically reliable causal connection

unsupported for: no genuine issue of material fact

unsupported for: failed to provide adequate protective measures

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

29059ms · graded 2026-08-28 08:22

25%hll-cl11264209-4wrongful-deathdifficulty 5private splitupstage/solar-pro4 · raw

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity50%×2

Citation checks

found460 U.S. 1 · in DocketRouter index

found514 U.S. 938 · in DocketRouter index

unverified564 U.S. 823 · verifier request budget exhausted

unverified858 F.2d 524 · verifier request budget exhausted

unverified962 F.2d 1363 · verifier request budget exhausted

unverified511 U.S. 379 · verifier request budget exhausted

found196 S.W.3d 774 · in DocketRouter index

unverified236 S.W.3d 256 · verifier request budget exhausted

found437 U.S. 463 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

supported460 U.S. 1 for: valid, irrevocable, and enforceable, save upon such grounds as exist at law or in equity for the revocation of any contract.

unsupported for: relies on the terms of the contract

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

148635ms · graded 2026-08-28 07:26

25%hll-cl11264209-3wrongful-deathdifficulty 4private splitupstage/solar-pro4 · raw

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity50%×2

Citation checks

found537 U.S. 79 · in DocketRouter index

found460 U.S. 1 · in DocketRouter index

unverified475 U.S. 612 · verifier request budget exhausted

found559 U.S. 662 · in DocketRouter index

found196 S.W.3d 774 · in DocketRouter index

found907 S.W.2d 517 · in DocketRouter index

unverified148 S.W.3d 221 · verifier request budget exhausted

unverified236 S.W.3d 298 · verifier request budget exhausted

unverified541 S.W.3d 118 · verifier request budget exhausted

unverified571 S.W.3d 893 · verifier request budget exhausted

Quote fidelity (every quotation must exist verbatim in its source)

no passage460 U.S. 1 for: arbitration agreements are interpreted under general contract principles,

no passage460 U.S. 1 for: when a party’s claims are within the scope of an arbitration clause, the FAA requires that they be resolved in arbitration.

supported559 U.S. 662 for: arbitration is a matter of consent, not coercion,

no passage559 U.S. 662 for: arbitration agreements on an equal footing with other contracts.

no passage907 S.W.2d 517 for: arising out of or relating to,

no passage541 S.W.3d 118 for: arising out of or relating to

unsupported for: denying a petition under section 4 of this title to order arbitration to proceed

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

149912ms · graded 2026-08-28 07:26

25%hll-cl11264209-1wrongful-deathdifficulty 4private splitupstage/solar-pro4 · raw

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity67%×2

Citation checks

found563 U.S. 333 · in DocketRouter index

unverified575 U.S. 208 · verifier request budget exhausted

found460 U.S. 1 · in DocketRouter index

found561 U.S. 63 · in DocketRouter index

unverified388 S.W.3d 614 · verifier request budget exhausted

unverified503 S.W.3d 777 · verifier request budget exhausted

found896 S.W.2d 156 · in DocketRouter index

unverified113 S.W.3d 441 · verifier request budget exhausted

Quote fidelity (every quotation must exist verbatim in its source)

supported563 U.S. 333 for: liberal federal policy favoring arbitration agreements.

supported575 U.S. 208 for: valid, irrevocable, and enforceable, save upon such grounds as exist at law or in equity for the revocation of any contract.

unsupported for: arise out of or relate to

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

145936ms · graded 2026-08-28 07:25

67%hll-cl11264209-2wrongful-deathdifficulty 5private splitupstage/solar-pro4 · raw

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity100%×2

Citation checks

found460 U.S. 1 · in DocketRouter index

found582 U.S. 1 · in DocketRouter index

found563 U.S. 333 · in DocketRouter index

found465 U.S. 1 · in DocketRouter index

found196 S.W.3d 774 · in DocketRouter index

in opinion180 S.W.3d 127

unverified148 S.W.3d 299 · verifier request budget exhausted

Quote fidelity (every quotation must exist verbatim in its source)

supported460 U.S. 1 for: liberal federal policy favoring arbitration agreements.

supported460 U.S. 1 for: shall be valid, irrevocable, and enforceable, save upon such grounds as exist at law or in equity for the revocation of any contract.

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

84211ms · graded 2026-08-28 07:24

0%hll-cl11264209-2wrongful-deathdifficulty 5private splitdeepseek/deepseek-v4-flash · 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.

180006ms · graded 2026-08-28 07:09

25%hll-cl11264209-1wrongful-deathdifficulty 4private splitdeepseek/deepseek-v4-flash · raw

Axes

Outcome50%×2

Standard-×2

Authority67%×2

Quote fidelity0%×2

Citation checks

in opinion279 S.W.3d 640

found166 S.W.3d 732 · in DocketRouter index

in opinion52 S.W.3d 749

found460 U.S. 1 · in DocketRouter index

found128 S.W.3d 223 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

unsupported for: shall be valid, irrevocable, and enforceable, save upon such grounds as exist at law or in equity for the revocation of any contract.

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

104935ms · graded 2026-08-28 07:07

55%hll-cl11264209-3wrongful-deathdifficulty 4private splitdeepseek/deepseek-v4-flash · raw

Axes

Outcome50%×2

Standard-×2

Authority60%×2

Quote fidelity-×2

Citation checks

found460 U.S. 1 · in DocketRouter index

found475 U.S. 643 · in DocketRouter index

found388 U.S. 395 · in DocketRouter index

in opinion279 S.W.3d 640

in opinion52 S.W.3d 749

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

47647ms · graded 2026-08-28 07:06

63%hll-cl11264209-4wrongful-deathdifficulty 5private splitdeepseek/deepseek-v4-flash · raw

Axes

Outcome50%×2

Standard-×2

Authority75%×2

Quote fidelity-×2

Citation checks

found539 U.S. 52 · in DocketRouter index

found841 S.W.2d 343 · in DocketRouter index

in opinion279 S.W.3d 640

found802 F.2d 1185 · in DocketRouter index

found816 F.2d 533 · in CourtListener bulk table

in opinion180 S.W.3d 127

found235 S.W.3d 185 · in DocketRouter index

in opinion52 S.W.3d 749

found465 U.S. 1 · in DocketRouter index

found460 U.S. 1 · in DocketRouter index

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

23345ms · graded 2026-08-28 07:06

67%hll-cl11117870-4wrongful-deathdifficulty 4private splitupstage/solar-pro4 · raw

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity100%×2

Citation checks

unverified554 S.W.3d 190 · verifier rate-limited

found260 S.W.3d 904 · in CourtListener bulk table

found872 S.W.2d 189 · in DocketRouter index

unverified302 S.W.3d 845 · verifier rate-limited

unverified148 S.W.3d 293 · verifier rate-limited

Quote fidelity (every quotation must exist verbatim in its source)

supported for: a factual and scientific basis for the assertion that the defendant’s failure to act caused the individual to contract a pandemic disease.

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

99235ms · graded 2026-08-28 06:56

50%hll-cl11117870-1wrongful-deathdifficulty 4private splitupstage/solar-pro4 · raw

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity100%×2

Citation checks

unverified571 S.W.3d 828 · verifier rate-limited

found615 S.W.3d 374 · in DocketRouter index

found630 S.W.3d 1 · in DocketRouter index

found596 S.W.3d 580 · in CourtListener bulk table

found460 S.W.3d 579 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

supported for: a factual and scientific basis for the assertion that the defendant’s failure to act caused the individual to contract a pandemic disease.

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

40402ms · graded 2026-08-28 06:55

50%hll-cl11117870-1wrongful-deathdifficulty 4private splitdeepseek/deepseek-v4-flash · raw

Axes

Outcome50%×2

Standard-×2

Authority0%×2

Quote fidelity100%×2

Citation checks

found79 S.W.3d 48 · in DocketRouter index

found328 S.W.3d 526 · in DocketRouter index

found543 S.W.3d 689 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

supported for: a factual and scientific basis for the assertion that the defendant’s failure to act caused the individual to contract a pandemic disease.

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

45939ms · graded 2026-08-28 06:48

25%hll-cl11117870-4wrongful-deathdifficulty 4private splitdeepseek/deepseek-v4-flash · raw

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity0%×2

Citation checks

found701 S.W.2d 238 · in DocketRouter index

found827 S.W.2d 833 · in DocketRouter index

found346 S.W.3d 546 · in DocketRouter index

Quote fidelity (every quotation must exist verbatim in its source)

unsupported for: A person may appeal from an interlocutory order of a district court denying a motion to dismiss filed under Section 148.004.

Private-split item: facts, answer key and answer withheld so the leaderboard stays uncontaminated. The scores above are complete.

13857ms · graded 2026-08-28 06:48