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-cl11231648-4defamationdifficulty 4private splitgoogle/gemini-3.7-flash · dr2

Axes

Outcome100%×2

Standard-×2

Authority75%×2

Quote fidelity-×2

Citation checks

in opinion591 S.W.3d 127

found462 S.W.3d 507 · in DocketRouter index

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

40346ms · graded 2026-08-28 22:37

88%hll-cl11231648-3defamationdifficulty 5private splitgoogle/gemini-3.7-flash · dr2

Axes

Outcome100%×2

Standard-×2

Authority75%×2

Quote fidelity-×2

Citation checks

found462 S.W.3d 507 · in DocketRouter index

in opinion591 S.W.3d 127

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

35639ms · graded 2026-08-28 22:36

80%hll-cl11231648-1defamationdifficulty 4private splitgoogle/gemini-3.7-flash · dr2

Axes

Outcome100%×2

Standard-×2

Authority60%×2

Quote fidelity-×2

Citation checks

in opinion591 S.W.3d 127

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

34091ms · graded 2026-08-28 22:36

88%hll-cl11231648-4defamationdifficulty 4private splitgoogle/gemini-3.7-flash · raw

Axes

Outcome100%×2

Standard-×2

Authority75%×2

Quote fidelity-×2

Citation checks

in opinion591 S.W.3d 127

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

29129ms · graded 2026-08-28 21:19

92%hll-cl11231648-3defamationdifficulty 5private splitgoogle/gemini-3.7-flash · raw

Axes

Outcome100%×2

Standard-×2

Authority75%×2

Quote fidelity100%×2

Citation checks

in opinion591 S.W.3d 127

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

supported for: while your business is with local men and their wives

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

26470ms · graded 2026-08-28 21:19

25%hll-cl11231648-1defamationdifficulty 4private splitgoogle/gemini-3.7-flash · raw

Axes

Outcome100%×2

Standard-×2

Authority60%×2

Quote fidelity0%×2

Citation checks

in opinion591 S.W.3d 127

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

unsupported for: requires a communication made in connection with a

unsupported for: *Id.* § 27.001(3). Under the amended TCPA (effective September 1, 2019), a

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

23906ms · graded 2026-08-28 21:19

0%hll-cl11231648-4defamationdifficulty 4private splitopenai/gpt-oss-20b · dr2

Axes

Outcome0%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found462 S.W.3d 507 · in DocketRouter index

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

found340 S.W.3d 432 · in DocketRouter index

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

70324ms · graded 2026-08-28 15:13

50%hll-cl11231648-3defamationdifficulty 5private splitopenai/gpt-oss-20b · dr2

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found462 S.W.3d 507 · in DocketRouter index

found340 S.W.3d 432 · in DocketRouter index

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

70807ms · graded 2026-08-28 15:12

30%hll-cl11231648-1defamationdifficulty 4private splitopenai/gpt-oss-20b · dr2

Axes

Outcome0%×2

Standard-×2

Authority60%×2

Quote fidelity-×2

Citation checks

in opinion591 S.W.3d 127

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

53070ms · graded 2026-08-28 15:11

50%hll-cl11231648-4defamationdifficulty 4private splitopenai/gpt-oss-120b · dr2

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found462 S.W.3d 507 · in DocketRouter index

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

84947ms · graded 2026-08-28 14:14

50%hll-cl11231648-3defamationdifficulty 5private splitopenai/gpt-oss-120b · dr2

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found94 S.W.3d 561 · in DocketRouter index

found909 F.2d 1035 · in DocketRouter index

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

43868ms · graded 2026-08-28 14:13

25%hll-cl11231648-1defamationdifficulty 4private splitopenai/gpt-oss-120b · dr2

Axes

Outcome100%×2

Standard-×2

Authority60%×2

Quote fidelity0%×2

Citation checks

found787 S.W.2d 348 · in DocketRouter index

found610 S.W.3d 763 · in DocketRouter index

in opinion591 S.W.3d 127

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

unsupported for: speech made in connection with a matter of public concern

unsupported for: whether the speech concerns a matter of public interest

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

34037ms · graded 2026-08-28 14:12

25%hll-cl11231648-4defamationdifficulty 4private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity33%×2

Citation checks

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

found462 S.W.3d 507 · in DocketRouter index

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

supported462 S.W.3d 507 for: in connection with a matter of public concern

unsupported for: a person’s private sexual relationships, even if they involve a married person, are not a matter of public concern merely because the person

unsupported for: based on or in response to a party’s exercise of the right of free speech

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

57976ms · graded 2026-08-28 11:54

67%hll-cl11231648-3defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity100%×2

Citation checks

found462 S.W.3d 507 · in DocketRouter index

found94 S.W.3d 561 · in DocketRouter index

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

supported94 S.W.3d 561 for: in connection with a matter of public concern,

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

51855ms · graded 2026-08-28 11:53

87%hll-cl11231648-1defamationdifficulty 4private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome100%×2

Standard-×2

Authority60%×2

Quote fidelity100%×2

Citation checks

in opinion591 S.W.3d 127

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

supported for: in connection with a matter of public concern.

supported for: these postings do not constitute communications made in connection with a matter of public concern

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

43383ms · graded 2026-08-28 11:52

0%hll-cl11231648-4defamationdifficulty 4private splitupstage/solar-pro4 · dr2

Axes

Outcome0%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found340 S.W.3d 432 · in DocketRouter index

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

32650ms · graded 2026-08-28 10:58

50%hll-cl11231648-3defamationdifficulty 5private splitupstage/solar-pro4 · dr2

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found721 F.2d 98 · in DocketRouter index

found909 F.2d 1035 · in DocketRouter index

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

85462ms · graded 2026-08-28 10:58

25%hll-cl11231648-1defamationdifficulty 4private splitupstage/solar-pro4 · dr2

Axes

Outcome100%×2

Standard-×2

Authority60%×2

Quote fidelity75%×2

Citation checks

in opinion591 S.W.3d 127

found271 S.W.3d 238 · in DocketRouter index

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

supported591 S.W.3d 127 for: made in connection with a matter of public concern.

unsupported for: is made in connection with an issue of public interest or public concern.

supported for: Hi [D] Why are you f@@cking married men?

supported for: why are you f@@cking married men while your business is with local men and their wives?

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

70084ms · graded 2026-08-28 10:57

0%hll-cl11231648-4defamationdifficulty 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.

77850ms · graded 2026-08-28 09:40

0%hll-cl11231648-1defamationdifficulty 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.

41567ms · graded 2026-08-28 09:39

0%hll-cl11231648-3defamationdifficulty 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.

36276ms · graded 2026-08-28 09:39

25%hll-cl11231648-4defamationdifficulty 4private splitopenai/gpt-oss-120b · raw

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity0%×2

Citation checks

found970 S.W.2d 1 · in DocketRouter index

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

unsupported for: the public‑concern test is a question of law, to be decided by the court, not by the jury.

unsupported for: the public‑concern test is a question of law, to be decided by the court, not by the jury,

unsupported for: the plaintiff’s own allegations that the fact is relevant to her business are not controlling.

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

111624ms · graded 2026-08-28 08:32

67%hll-cl11231648-3defamationdifficulty 5private splitopenai/gpt-oss-120b · raw

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity100%×2

Citation checks

found939 S.W.2d 1 · in CourtListener bulk table

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

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

supported for: Why are you f@@cking married men?

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

33573ms · graded 2026-08-28 08:31

0%hll-cl11231648-1defamationdifficulty 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.

6863ms · graded 2026-08-28 08:30

67%hll-cl11231648-4defamationdifficulty 4private splitupstage/solar-pro4 · raw

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity100%×2

Citation checks

found469 S.W.3d 360 · in CourtListener bulk table

unverified533 S.W.3d 333 · verifier request budget exhausted

found517 S.W.3d 464 · in CourtListener bulk table

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

supported for: a communication made in connection with a matter of public concern.

supported for: Why are you f@@cking married men?

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

90111ms · graded 2026-08-28 07:12

17%hll-cl11231648-1defamationdifficulty 4private splitupstage/solar-pro4 · raw

Axes

Outcome0%×2

Standard-×2

Authority0%×2

Quote fidelity50%×2

Citation checks

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

unverified510 S.W.3d 406 · verifier request budget exhausted

unverified472 U.S. 79 · verifier request budget exhausted

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

unsupported for: ). These communications plainly fall within the TCPA's definition of

unsupported for: as they are communications made in connection with a matter of public concern. The content of the posts concerns [D]'s alleged conduct as a

supported for: while your business is with local men and their wives

supported for: Why are you f@@cking married men?

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

57003ms · graded 2026-08-28 07:11

13%hll-cl11231648-3defamationdifficulty 5private splitupstage/solar-pro4 · raw

Axes

Outcome0%×2

Standard-×2

Authority0%×2

Quote fidelity40%×2

Citation checks

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

unverified372 S.W.3d 299 · verifier request budget exhausted

unverified516 S.W.3d 420 · verifier request budget exhausted

unverified482 S.W.3d 168 · verifier request budget exhausted

unverified430 S.W.3d 530 · verifier request budget exhausted

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

unsupported for: a topic of legal, political, or social interest to the public at large, as distinguished from a matter of purely private concern.

unsupported for: social interest to the public at large.

supported for: Why are you f@@cking married men?

unsupported for: social interest to the public at large.

supported for: support all women and stand against homewreckers

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

49732ms · graded 2026-08-28 07:11

25%hll-cl11231648-1defamationdifficulty 4private splitdeepseek/deepseek-v4-flash · raw

Axes

Outcome100%×2

Standard-×2

Authority60%×2

Quote fidelity80%×2

Citation checks

in opinion591 S.W.3d 127

unverified567 S.W.3d 733 · verifier rate-limited

in opinion515 S.W.3d 878

found512 S.W.3d 895 · in DocketRouter index

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

supported for: in connection with a matter of public concern

unsupported for: based on, relates to, or is in response to

supported for: Exercise of the right of free speech

supported for: in connection with a matter of public concern.

supported for: while your business is with local men and their wives

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

53242ms · graded 2026-08-28 06:58

33%hll-cl11231648-4defamationdifficulty 4private splitdeepseek/deepseek-v4-flash · raw

Axes

Outcome0%×2

Standard-×2

Authority0%×2

Quote fidelity100%×2

Citation checks

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

found573 S.W.3d 418 · in DocketRouter index

found438 S.W.3d 847 · in DocketRouter index

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

supported for: in connection with a matter of public concern

supported for: based on or in response to

supported for: in connection with a matter of public concern.

no passage460 S.W.3d 579 for: be fairly considered as relating to a matter of political, social, or other interest to the community.

supported for: Hi [D] Why are you f@@cking married men?

supported for: Hi [D] why are you f@@cking married men while your business is with local men and their wives?

supported for: I am not sure if anyone has used this lady [D] as their realtor … but I think it’s important to support all women and stand against homewrec

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

33684ms · graded 2026-08-28 06:58

25%hll-cl11231648-3defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · raw

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity67%×2

Citation checks

found624 S.W.3d 796 · in DocketRouter index

in opinion515 S.W.3d 878

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

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

supported for: in connection with a matter of public concern.

supported for: Why are you f@@cking married men?

supported for: your business is with local men.

unsupported for: good, product, or service in the marketplace

unsupported for: the TCPA does not exist to protect communications about purely private matters, even if those communications are made in a public forum.

supported for: in connection with a matter of public concern.

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

28109ms · graded 2026-08-28 06:58

0%hll-flp11070303-2defamationdifficulty 4private 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.

182843ms · graded 2026-08-27 16:42

21%hll-flp9941893-3defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · raw

Axes

Outcome0%×2

Standard-×2

Authority64%×2

Quote fidelity0%×2

Citation checks

in opinion418 S.W.3d 52

in opinion38 S.W.3d 103

found94 S.W.3d 561 · in DocketRouter index

found529 S.W.3d 429 · in DocketRouter index

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

unsupported for: based on, relates to, or is in response to

unsupported for: made demeaning comments during post-conviction proceedings

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

77851ms · graded 2026-08-27 13:22

0%hll-flp9375253-2defamationdifficulty 3private 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.

189825ms · graded 2026-08-27 13:21

25%hll-flp9941893-2defamationdifficulty 3private splitdeepseek/deepseek-v4-flash · raw

Axes

Outcome100%×2

Standard-×2

Authority63%×2

Quote fidelity0%×2

Citation checks

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

in opinion418 S.W.3d 52

found94 S.W.3d 561 · in DocketRouter index

unverified438 S.W.3d 89 · search unavailable

found591 S.W.3d 127 · in DocketRouter index

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

no passage460 S.W.3d 579 for: the defendant's exercise of the right of free speech. Tex. Civ. Prac. & Rem. Code § 27.003(a). Once the movant demonstrates that the action

no passage94 S.W.3d 561 for: —that is, if it is no more damaging to the plaintiff's reputation than the truth would have been. *Id.* at 62–63. The substantial-truth inqu

unsupported for: of that man. The prosecutor argues he was not licensed at the time of the original 1980s conviction and never formally assisted in post-con

no passage438 S.W.3d 89 for: in common usage encompasses the entire criminal process, including post-conviction proceedings. *See, e.g., Ex parte Ghahate*, 438 S.W.3d 8

no passage438 S.W.3d 89 for: as part of the prosecution). The article's gist is that the prosecutor had some connection to the case that led to the wrongful conviction.

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

70061ms · graded 2026-08-27 13:20

50%hll-flp6110664-3defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · raw

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found797 S.W.2d 66 · in DocketRouter index

found868 S.W.2d 822 · in DocketRouter index

found749 S.W.2d 762 · in DocketRouter index

found554 S.W.3d 614 · in DocketRouter index

found164 S.W.3d 656 · in DocketRouter index

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

31543ms · graded 2026-08-27 13:19

0%hll-flp6110083-3defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · raw

Axes

Outcome0%×2

Standard-×2

Authority0%×2

Quote fidelity0%×2

Citation checks

found119 S.W.3d 707 · in DocketRouter index

found871 S.W.2d 697 · in DocketRouter index

found113 S.W.3d 340 · in DocketRouter index

found629 S.W.2d 919 · in DocketRouter index

unverified40 S.W.3d 537 · search unavailable

unverified631 S.W.3d 290 · search unavailable

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

no passage113 S.W.3d 340 for: Even constitutional claims may be waived if not raised in the trial court.

unsupported for: construed as arguing the trial court did not err

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

45413ms · graded 2026-08-27 13:19

25%hll-flp5287665-3defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · raw

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity0%×2

Citation checks

in opinion94 S.W.3d 561

found554 S.W.3d 614 · in DocketRouter index

in opinion776 S.W.2d 567

found497 U.S. 1 · in DocketRouter index

unverified166 S.W.3d 344 · search unavailable

found797 S.W.2d 66 · in DocketRouter index

found38 S.W.3d 103 · in DocketRouter index

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

no passage554 S.W.3d 614 for: exposes a person to public hatred, contempt, ridicule, or financial injury.

unsupported38 S.W.3d 103 for: an account of trial evidence and argument, with the author’s opinions.

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

34247ms · graded 2026-08-27 13:16

0%hll-flp4693156-2defamationdifficulty 5private splitblankdeepseek/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.

28677ms · graded 2026-08-27 13:11

88%hll-flp9941893-2defamationdifficulty 3private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome100%×2

Standard-×2

Authority75%×2

Quote fidelity-×2

Citation checks

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

found529 S.W.3d 429 · in DocketRouter index

in opinion418 S.W.3d 52

in opinion38 S.W.3d 103

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

49415ms · graded 2026-08-26 21:41

58%hll-flp9375253-2defamationdifficulty 3private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome0%×2

Standard-×2

Authority75%×2

Quote fidelity100%×2

Citation checks

in opinion554 S.W.3d 614

found418 S.W.3d 52 · in DocketRouter index

in opinion94 S.W.3d 561

found529 S.W.3d 429 · in DocketRouter index

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

supported for: help pregnant Mothers murder their babies,

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

40137ms · graded 2026-08-26 21:40

82%hll-flp9941893-3defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome100%×2

Standard-×2

Authority64%×2

Quote fidelity-×2

Citation checks

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

in opinion418 S.W.3d 52

in opinion38 S.W.3d 103

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

75905ms · graded 2026-08-26 21:33

0%hll-flp6110664-3defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome0%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

in opinion168 S.W.3d 802

found67 S.W.3d 870 · in DocketRouter index

found7 S.W.3d 801 · in DocketRouter index

in opinion418 U.S. 323

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

no passage67 S.W.3d 870 for: A newspaper … is privileged to publish … a fair, true, and impartial account of … a judicial proceeding.

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

129315ms · graded 2026-08-26 21:21

0%hll-flp6110083-3defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome0%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found852 S.W.2d 440 · in DocketRouter index

found119 S.W.3d 707 · in DocketRouter index

unverified158 S.W.3d 496 · search unavailable

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

31238ms · graded 2026-08-26 21:18

50%hll-flp5287665-3defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

in opinion168 S.W.3d 802

found38 S.W.3d 103 · in DocketRouter index

unverified68 S.W.3d 5 · search unavailable

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

33748ms · graded 2026-08-26 21:09

89%hll-flp4693156-2defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · dr2

Axes

Outcome100%×2

Standard-×2

Authority67%×2

Quote fidelity100%×2

Citation checks

found356 S.W.3d 407 · in DocketRouter index

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

supported for: may maintain an action for defamation only if

supported for: may file a plea in abatement

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

177973ms · graded 2026-08-26 21:05

25%hll-flp9941893-2defamationdifficulty 3private splitdeepseek/deepseek-v4-flash · juiced

Axes

Outcome100%×2

Standard-×2

Authority75%×2

Quote fidelity0%×2

Citation checks

in opinion418 S.W.3d 52

in opinion38 S.W.3d 103

in opinion794 S.W.2d 14

found94 S.W.3d 561 · in DocketRouter index

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

unsupported for: based on, relates to, or is in response to

unsupported418 S.W.3d 52 for: clear and specific evidence a prima facie case for each essential element of the claim in question.

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

321149ms · graded 2026-08-26 13:52

25%hll-flp9375253-2defamationdifficulty 3private splitdeepseek/deepseek-v4-flash · juiced

Axes

Outcome0%×2

Standard-×2

Authority75%×2

Quote fidelity43%×2

Citation checks

in opinion94 S.W.3d 561

in opinion497 U.S. 1

unverified662 S.W.3d 854 · search unavailable

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

supported for: exist to help pregnant Mothers murder their babies

unsupported for: based on or in response to

unsupported94 S.W.3d 561 for: by clear and specific evidence a prima facie case for each essential element of the claim in question.

unsupported497 U.S. 1 for: the entire conversation or publication, not just an excerpt.

unsupported for: Accusing an abortion-rights organization of being a ‘criminal organization’ and of ‘murdering babies’ are statements that, in context, const

supported for: exist to help pregnant Mothers murder their babies.

supported for: an act of murder with malice aforethought.

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

300151ms · graded 2026-08-26 13:50

25%hll-flp9941893-3defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · juiced

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: as the literal truth, even if it contains minor inaccuracies. *Polk County Publishing Co. v. Coleman*, No. 22-0645, 2024 WL 2813679, at *4

unsupported for: of the publication as a whole, not isolated statements. *Id.* A statement is substantially true if the

unsupported for: —was substantially true because the prosecutor had been

unsupported for: *Polk County*, 2024 WL 2813679, at *5. The court emphasized that

unsupported for: is a broad term encompassing a range of conduct, and that the

unsupported for: in the prosecution, even if not formal participation in the initial trial. The

unsupported for: of the article—that the prosecutor had some connection to the wrongful conviction case—is substantially true. The article's failure to spec

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

220951ms · graded 2026-08-26 13:17

0%hll-flp6110664-3defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · juiced

Axes

Outcome0%×2

Standard-×2

Authority0%×2

Quote fidelity-×2

Citation checks

found573 S.W.3d 781 · in DocketRouter index

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

354583ms · graded 2026-08-26 12:53

0%hll-flp6110083-3defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · juiced

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.

425351ms · graded 2026-08-26 12:44

25%hll-flp5287665-3defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · juiced

Axes

Outcome100%×2

Standard-×2

Authority0%×2

Quote fidelity60%×2

Citation checks

no citations offered

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

unsupported for: there are no genuinely disputed facts that would prevent a judgment in favor of the party.

unsupported for: fair, true, and impartial account of . . . a judicial proceeding.

supported for: fairly attributes negative assertions about the family to Shah's trial testimony and adequately informs the reader of conflicts in the testi

supported for: would not perceive it to impugn the family's character,

supported for: fairly attributes negative assertions about the family to [the witness's] trial testimony and adequately informs the reader of conflicts in

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

502273ms · graded 2026-08-26 12:24

25%hll-flp4693156-2defamationdifficulty 5private splitdeepseek/deepseek-v4-flash · juiced

Axes

Outcome100%×2

Standard-×2

Authority83%×2

Quote fidelity33%×2

Citation checks

no citations offered

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

unsupported for: relying on the statute's language that a plaintiff

supported for: may maintain an action for defamation only if

unsupported for: ) creating a condition precedent. Section 73.062 provides a separate remedy for a defendant who

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

368999ms · graded 2026-08-26 12:15