Benchmark Almanac

ExpertEval

Ours (SFT, Heavy) 68.9% tops its leaderboard Claude Opus 4.6 66.9% leads the models we track
Not in model cards

Models answer cases in medicine, finance and law. Practicing professionals write the cases and supply weighted grading rubrics.

The published rankings compare more than five systems, including Claude, GPT, Qwen, Gemini, Kimi and GLM.

Made by
UniPat AI
Released
May 2026
Kind
Other professions
Level
Expert
Scored
Graded by a model
Answers
Open-ended
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Written by experts
Refresh
One fixed set
Run by
A host
Occupations
Business and financial operations, Legal, Healthcare practitioners and technical
Strongest model tested
GPT-5.4 #28 on the capability index
Last model added
March 2026
Scores refreshed
November 21st, 2026
11
Entries on its own leaderboard, 7 models we track

Ours (SFT, Heavy) tops the leaderboard with 68.9% Claude Opus 4.6 leads with 66.9% among models released by March 2026

Best score per entry from the benchmark's own leaderboard, read on November 21st, 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. The best model we track is Claude Opus 4.6, at 66.9%. This view shows only models we track, each at its best.

The newest model with a score here came out in March 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 Ours (SFT, Heavy) 68.9%
  2. 2 Claude Opus 4.6 66.9%
  3. 3 Ours (SFT) 66.2%
  4. 4 GPT-5.4 high 66.2%
  5. 5 Qwen 3.6 Plus 63.3%
  6. 6 Gemini 3.1 Pro 63%
  7. 7 GLM-5 59.3%
  8. 8 Kimi K2.5 58.2%
  9. 9 Seed2.0 Pro 56.2%
  10. 10 Ours (Baseline) 54.8%
  11. 11 Qwen3-Deep-Research 48.5%

Source: Official ExpertEval leaderboard

#EntryScoreSettingDateSource
1 Ours (SFT, Heavy) 68.9% Official leaderboard
2 Claude Opus 4.6 66.9% Feb 2026 Official leaderboard
3 Ours (SFT) 66.2% Official leaderboard
4 GPT-5.4 66.2% high Mar 2026 Official leaderboard
5 Qwen 3.6 Plus 63.3% Mar 2026 Official leaderboard
6 Gemini 3.1 Pro 63% Feb 2026 Official leaderboard
7 GLM-5 59.3% Feb 2026 Official leaderboard
8 Kimi K2.5 58.2% Jan 2026 Official leaderboard
9 Seed2.0 Pro 56.2% Feb 2026 Official leaderboard
10 Ours (Baseline) 54.8% Official leaderboard
11 Qwen3-Deep-Research 48.5% Official leaderboard
#ModelScoreSettingDateSource
1 Claude Opus 4.6 66.9% Feb 2026 Official leaderboard
2 GPT-5.4 66.2% high Mar 2026 Official leaderboard
3 Qwen 3.6 Plus 63.3% Mar 2026 Official leaderboard
4 Gemini 3.1 Pro 63% Feb 2026 Official leaderboard
5 GLM-5 59.3% Feb 2026 Official leaderboard
6 Kimi K2.5 58.2% Jan 2026 Official leaderboard
7 Seed2.0 Pro 56.2% Feb 2026 Official leaderboard

Number one over time

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

Anthropic
Own leaderboard Not tested since May 2026

Source: Official ExpertEval 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 Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 4.6 Kimi K2.5 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 4.6 Kimi K2.5

Source: Official ExpertEval 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 10 checks pass, 2 warnings. 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 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (11 entries).
  • Pass Models scored 7 models we track, plus 4 other entries on its leaderboard.
  • Warning Newest score The newest came 8 months ago, in March 2026, for Qwen 3.6 Plus.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.4 (#28).
  • Pass Headroom The best is 66.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on unipat.ai: 7 rows for models we track and 4 other entries at the last read.
  • Pass Last read November 21st, 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