Numerical results extraction from randomized controlled trials
Models extract group sizes, event counts, means, and standard deviations from trial reports. The test contains 656 treatment comparisons across 110 papers.
67AI Lab tested seven models on 648 comparisons from 109 available papers. Its table reports the share of correctly filled cells.
- Made by
- Northeastern University and King's College London
- Released
- May 2024
- Kind
- Medicine
- Level
- University
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Subject
- Clinical medicine, Mathematics
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Biology and medicine
- Strongest model tested
- Claude Opus 5.5 #5 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
DeepSeek V4.1 Flash leads with 77.9% among models released by September 2026
Best score per model from 67AI Lab’s leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.
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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6.1 Sol
- and 15 more
- 1
DeepSeek V4.1 Flash Exact (median) 77.9%
- 2 Claude Opus 5.5 Exact (median) 75.8%
- 3
Qwen 3.6 35B-A3B Greedy 75.5%
- 4
Qwen3-Coder-Next Greedy 74.7%
- 5
Gemma 4 26B A4B Greedy 73.8%
- 6
Qwen 3.8 27B Greedy 72.3%
- 7
Nemotron 3.5 Lightning 30B-A3B Greedy 62.7%
Source: 67AI Lab’s leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 77.9% | Exact (median) | Sep 2026 | Official leaderboard |
| 2 | Claude Opus 5.5 | 75.8% | Exact (median) | Sep 2026 | Official leaderboard |
| 3 | | 75.5% | Greedy | Apr 2026 | Official leaderboard |
| 4 | | 74.7% | Greedy | Feb 2026 | Official leaderboard |
| 5 | | 73.8% | Greedy | Apr 2026 | Official leaderboard |
| 6 | | 72.3% | Greedy | Aug 2026 | Official leaderboard |
| 7 | | 62.7% | Greedy | Aug 2026 | Official leaderboard |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: 67AI Lab’s leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Exact (median) | 77.9% | ||||
| Claude Opus 5.5 | Exact (median) | 75.8% | |||
| Greedy | 75.5% | ||||
| Greedy | 74.7% | ||||
| Exact (median) | 74.2% | ||||
| Greedy | 73.8% | ||||
| Exact (median) | 73.3% | ||||
| Exact (median) | 72.9% | ||||
| Greedy | 72.3% | ||||
| Exact (median) | 71.5% | ||||
| Greedy | 62.7% | ||||
| Exact (median) | 59.6% |
3 models have held number one on 67AI Lab’s leaderboard since its release in May 2024
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: 67AI Lab’s leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: 67AI Lab’s 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
- 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 official leaderboard (7 entries).
- Pass Models scored 7 models we track.
- Pass Newest score The newest is from September 2026, for Claude Opus 5.5.
- Note Frontier models Only 1 of the top 10 has a score. The strongest tested is Claude Opus 5.5 (#5).
- Pass Headroom The best is 77.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on 67AI Lab: 12 rows for models we track 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.