Benchmark Almanac

SuperCLUE-Law

Kimi K3 92.1 leads since July 2026
Not in model cards

Models respond to Chinese legal questions.

SuperCLUE reports scores in a public workbook.

Made by
SuperCLUE
Kind
Law
Level
Expert
Scored
Graded by people
Answers
Open-ended
Measures
Capability
Subject
Law
Language
Chinese
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
A host
In views
Law and finance
Strongest model tested
Kimi K3 #25 on the capability index
Last model added
August 2026
Scores refreshed
November 20th, 2026
11
Entries on its own leaderboard, 10 models we track

Kimi K3 leads with 92.1 among models released by August 2026 Kimi K3 leads with 92.1 among models released by August 2026

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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 August 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 Kimi K3 92.1
  2. 2 Qwen 3.8 Max 90.6
  3. 3 Seed2.1 Pro high 85.3
  4. 4 DeepSeek-V4-Flash max 85.2
  5. 5 Tencent Hy3 high 83.4
  6. 6 MiniMax-M3 80.0
  7. 7 DeepSeek-V4-Pro(max) Preview 预览版本 78.7
  8. 8 LongCat-2.0 77.5
  9. 9 Step 3.7 Flash high 77.2
  10. 10 GLM-5.2 max 74.0
  11. 11 MiMo-V2.5-Pro 68.5

Source: Official SuperCLUE-Law leaderboard

#EntryScoreSettingDateSource
1 Kimi K3 92.1 Jul 2026 Official leaderboard
2 Qwen 3.8 Max 90.6 Aug 2026 Official leaderboard
3 Seed2.1 Pro 85.3 high Jun 2026 Official leaderboard
4 DeepSeek-V4-Flash 85.2 max Apr 2026 Official leaderboard
5 Tencent Hy3 83.4 high Jul 2026 Official leaderboard
6 MiniMax-M3 80.0 Jun 2026 Official leaderboard
7 DeepSeek-V4-Pro(max) Preview 预览版本 78.7 Official leaderboard
8 LongCat-2.0 77.5 Jul 2026 Official leaderboard
9 Step 3.7 Flash 77.2 high May 2026 Official leaderboard
10 GLM-5.2 74.0 max Jun 2026 Official leaderboard
11 MiMo-V2.5-Pro 68.5 Apr 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Kimi K3 92.1 Jul 2026 Official leaderboard
2 Qwen 3.8 Max 90.6 Aug 2026 Official leaderboard
3 Seed2.1 Pro 85.3 high Jun 2026 Official leaderboard
4 DeepSeek-V4-Flash 85.2 max Apr 2026 Official leaderboard
5 Tencent Hy3 83.4 high Jul 2026 Official leaderboard
6 MiniMax-M3 80.0 Jun 2026 Official leaderboard
7 LongCat-2.0 77.5 Jul 2026 Official leaderboard
8 Step 3.7 Flash 77.2 high May 2026 Official leaderboard
9 GLM-5.2 74.0 max Jun 2026 Official leaderboard
10 MiMo-V2.5-Pro 68.5 Apr 2026 Official leaderboard

Rankings by part

We read 7 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as 法律文本审核, 法律材料生成 and 咨询交互服务. Kimi K3 leads 4 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

法律文本审核

10 models we track have a score here.

  1. 1 Kimi K3 93.7
  2. 2 Qwen 3.8 Max 91.2
  3. 3 DeepSeek-V4-Flash ↑1 87.5
  4. 4 Seed2.1 Pro ↓1 86.2
  5. 5 MiniMax-M3 ↑1 85.7
  6. 6 Tencent Hy3 ↓1 82.3
  7. 7 LongCat-2.0 79.8
  8. 8 Step 3.7 Flash 78.5
  9. 9 GLM-5.2 71.5
  10. 10 MiMo-V2.5-Pro 62.4

4 models have held number one on the official leaderboard since 2023

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

Xiaomi Corp DeepSeek ByteDance Seed Moonshot AI
Own leaderboard Not tested since Aug 2026
Kimi K3 92.1

Source: Official SuperCLUE-Law leaderboard

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
On the benchmark’s own leaderboard
70.0 80.0 90.0 2026 70.0 80.0 90.0 2026

Source: Official SuperCLUE-Law 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

8 of 9 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (11 entries).
  • Pass Models scored 10 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from August 2026, for Qwen 3.8 Max.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Kimi K3 (#25).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on superclueai.com: 10 rows for models we track and 1 other entry 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