Benchmark Almanac

LexPilot

Claude Opus 5 72.1% leads since October 2026
Not in model cards

Models interview a user about a Chinese civil case and predict the ruling on each claim. Paired consultations reveal the effect of missing facts.

Released
October 2026
Kind
Law
Level
Expert
Scored
Graded by a model
Answers
Agent task
Tasks
All public
Measures
Capability
Subject
Law
Language
Chinese
In and out
Text → Text
Interaction
Multi-turn
Refresh
One fixed set
Run by
Anyone
In views
Law and finance
Strongest model tested
Claude Opus 5 #11 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
10
Entries in its paper, 8 models we track

Claude Opus 5 leads with 72.1% among models released by September 2026 Claude Opus 5 leads with 72.1% among models released by September 2026

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports separate consultation tasks. The headline is macro F1 for Legal Completeness Assessment, expressed as a percentage. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Claude Opus 5 72.1%
  2. 2 GPT-5.6 Sol 70.7%
  3. 3 Gemini 3.8 Flash 70.4%
  4. 4 LegalOne-8B 67.7%
  5. 5 GLM-5.3 65%
  6. 6 Kimi K3 64%
  7. 7 MiniMax-M3 63.3%
  8. 8 DeepSeek-V4-Pro 61.5%
  9. 9 Qwen 3.8 Max 59.6%
  10. 10 LawLLM-7B 41.9%

Source: The LexPilot paper

#EntryScoreSettingDateSource
1 Claude Opus 5 72.1% Jul 2026 Official leaderboard
2 GPT-5.6 Sol 70.7% Jul 2026 Official leaderboard
3 Gemini 3.8 Flash 70.4% Sep 2026 Official leaderboard
4 LegalOne-8B 67.7% Official leaderboard
5 GLM-5.3 65% Aug 2026 Official leaderboard
6 Kimi K3 64% Jul 2026 Official leaderboard
7 MiniMax-M3 63.3% Jun 2026 Official leaderboard
8 DeepSeek-V4-Pro 61.5% Apr 2026 Official leaderboard
9 Qwen 3.8 Max 59.6% Aug 2026 Official leaderboard
10 LawLLM-7B 41.9% Official leaderboard
#ModelScoreSettingDateSource
1 Claude Opus 5 72.1% Jul 2026 Official leaderboard
2 GPT-5.6 Sol 70.7% Jul 2026 Official leaderboard
3 Gemini 3.8 Flash 70.4% Sep 2026 Official leaderboard
4 GLM-5.3 65% Aug 2026 Official leaderboard
5 Kimi K3 64% Jul 2026 Official leaderboard
6 MiniMax-M3 63.3% Jun 2026 Official leaderboard
7 DeepSeek-V4-Pro 61.5% Apr 2026 Official leaderboard
8 Qwen 3.8 Max 59.6% Aug 2026 Official leaderboard

Rankings by part

We read 29 parts from the benchmark’s paper in 4 groups: legal completeness assessment, detail completion guidance, interaction-based ljp and gold-standard ljp. Each ranks models on one part of the test. Claude Opus 5 leads 16 of them, and 4 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Direct LJP

Quadratic weighted kappa. 8 models we track have a score here.

  1. 1 Claude Opus 5 0.43
  2. 2 GPT-5.6 Sol 0.43
  3. 3 GLM-5.3 ↑1 0.38
  4. 4 MiniMax-M3 ↑2 0.38
  5. 5 Gemini 3.8 Flash ↓2 0.36
  6. 6 DeepSeek-V4-Pro ↑1 0.35
  7. 7 Qwen 3.8 Max ↑1 0.35
  8. 8 Kimi K3 ↓3 0.32

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic
Benchmark paper Not tested since Oct 2026

Source: The LexPilot paper

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 5 MiniMax-M3 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 5 MiniMax-M3

Source: Official LexPilot leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Law, finance and medicine

All 637 in Law, finance and medicine
  • MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy. Qwen 3.8 Max 80.4%
  • HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
  • HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
  • FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy. Ling-3.1-flash 81.7%
  • KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
  • Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%

Data audit

All 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (10 entries).
  • Pass Models scored 8 models we track, plus 2 other entries on its leaderboard.
  • Pass Newest score The newest is from September 2026, for Gemini 3.8 Flash.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Opus 5 (#11).
  • Pass Headroom The best is 72.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 8 rows for models we track and 2 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check