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

88%hll-cl11261323-3conversiondifficulty 4private splitgoogle/gemini-3.7-flash · dr2

Axes

Outcome100%×2

Standard100%×2

Authority63%×2

Quote fidelity-×2

Citation checks

found46 S.W.3d 237 · in DocketRouter index

found767 S.W.2d 686 · in DocketRouter index

in opinion168 S.W.3d 802

found945 S.W.2d 895 · in DocketRouter index

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

26042ms · graded 2026-08-28 23:10

88%hll-cl11261323-3conversiondifficulty 4private splitgoogle/gemini-3.7-flash · raw

Axes

Outcome100%×2

Standard100%×2

Authority63%×2

Quote fidelity-×2

Citation checks

found46 S.W.3d 237 · in DocketRouter index

found767 S.W.2d 686 · in DocketRouter index

in opinion168 S.W.3d 802

found474 S.W.2d 444 · in DocketRouter index

unverified677 S.W.3d 83 · verifier request budget exhausted

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

16993ms · graded 2026-08-28 21:25

33%hll-cl11261323-3conversiondifficulty 4private splitopenai/gpt-oss-20b · dr2

Axes

Outcome0%×2

Standard100%×2

Authority0%×2

Quote fidelity-×2

Citation checks

found244 S.W.2d 660 · in DocketRouter index

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

148905ms · graded 2026-08-28 16:24

25%hll-cl11261323-3conversiondifficulty 4private splitopenai/gpt-oss-120b · dr2

Axes

Outcome100%×2

Standard100%×2

Authority0%×2

Quote fidelity0%×2

Citation checks

found850 S.W.2d 752 · in DocketRouter index

found629 S.W.2d 694 · in DocketRouter index

found284 S.W.2d 138 · in DocketRouter index

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

unsupported for: view the evidence favorable to the trial court’s findings and disregard contrary evidence if a reasonable fact‑finder could do so

unsupported for: everything on the lot was included

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

51378ms · graded 2026-08-28 15:07

88%hll-cl11261323-3conversiondifficulty 4private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome100%×2

Standard100%×2

Authority63%×2

Quote fidelity-×2

Citation checks

found46 S.W.3d 237 · in DocketRouter index

in opinion168 S.W.3d 802

found474 S.W.2d 444 · in DocketRouter index

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

55649ms · graded 2026-08-28 12:56

67%hll-cl11261323-3conversiondifficulty 4private splitupstage/solar-pro4 · dr2

Axes

Outcome100%×2

Standard100%×2

Authority0%×2

Quote fidelity-×2

Citation checks

found46 S.W.3d 237 · in DocketRouter index

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

117900ms · graded 2026-08-28 12:03

0%hll-cl11261323-3conversiondifficulty 4private splitblankopenai/gpt-oss-20b · raw

Axes

Outcome0%×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.

48236ms · graded 2026-08-28 09:47

25%hll-cl11261323-3conversiondifficulty 4private splitopenai/gpt-oss-120b · raw

Axes

Outcome100%×2

Standard100%×2

Authority0%×2

Quote fidelity0%×2

Citation checks

unverified200 S.W.3d 1005 · verifier rate-limited

found199 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: a conversion is an intentional tort that occurs when a person intentionally exercises control over the personal property of another in a man

unsupported for: a plaintiff must first establish a legally protected interest in the property, typically ownership or a possessory right, before a conversio

unsupported for: everything on the lot is included

unsupported for: everything on the lot was included in the sale.

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

93216ms · graded 2026-08-28 08:40

25%hll-cl11261323-3conversiondifficulty 4private splitupstage/solar-pro4 · raw

Axes

Outcome100%×2

Standard100%×2

Authority0%×2

Quote fidelity0%×2

Citation checks

found168 S.W.3d 808 · cached

found29 S.W.3d 580 · in DocketRouter index

unverified981 S.W.2d 229 · verifier request budget exhausted

unverified202 S.W.3d 301 · verifier request budget exhausted

unverified202 S.W.3d 824 · verifier request budget exhausted

found327 S.W.3d 118 · in DocketRouter index

unverified443 S.W.3d 107 · verifier request budget exhausted

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

unsupported for: so weak as to do no more than create a mere surmise or suspicion.

unsupported for: only equal to or less than the contrary evidence.

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

34856ms · graded 2026-08-28 07:22

88%hll-cl11261323-3conversiondifficulty 4private splitdeepseek/deepseek-v4-flash · raw

Axes

Outcome100%×2

Standard100%×2

Authority63%×2

Quote fidelity-×2

Citation checks

in opinion168 S.W.3d 802

found474 S.W.2d 444 · in DocketRouter index

found190 S.W.3d 263 · in DocketRouter index

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

no passage474 S.W.2d 444 for: rises to a level that would enable reasonable and fair-minded people to differ in their conclusions.

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

41006ms · graded 2026-08-28 07:06