Benchmark Almanac

LABBench2 TrialQA

GPT-5.2 Pro 93.3% leads since February 2026
Not in model cards

Models use clinical trial records to answer research questions.

The publisher reports model results for this evaluation.

Released
February 2026
Kind
Research science
Level
Expert
Scored
Checked automatically
Answers
Multiple choice
Tasks
Public, plus a private test set
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
A host
Based on
LABBench2
Strongest model tested
GPT-5.2 Pro #32 on the capability index
Last model added
February 2026
Scores refreshed
November 20th, 2026
5
Models scored on its own leaderboard

GPT-5.2 Pro leads with 93.3% among models released by February 2026

Best score per model from the benchmark's own 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 February 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 GPT-5.2 Pro inject / tools,high 93.3%
  2. 2 GPT-5.2 inject / tools,high 90.8%
  3. 3 Gemini 3 Pro inject / tools,high 80%
  4. 4 Claude Opus 4.6 inject / tools,high 49.2%
  5. 5 Claude Opus 4.5 inject / tools,high 47.5%

Source: Official LABBench2 TrialQA leaderboard

#ModelScoreSettingReleasedRun onSource
1 GPT-5.2 Pro 93.3% inject / tools,high Dec 2025 Feb 2026 Official leaderboard
2 GPT-5.2 90.8% inject / tools,high Dec 2025 Feb 2026 Official leaderboard
3 Gemini 3 Pro 80% inject / tools,high Nov 2025 Feb 2026 Official leaderboard
4 Claude Opus 4.6 49.2% inject / tools,high Feb 2026 Mar 2026 Official leaderboard
5 Claude Opus 4.5 47.5% inject / tools,high Nov 2025 Mar 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.

Lowest effort to highest, light to dark
GPT-5.2 Pro
inject inject / to…
93.3%
GPT-5.2
inject inject / to…
90.8%
Gemini 3 Pro
inject inject / to…
80%
Claude Opus 4.6
inject inject / to…
49.2%
Claude Opus 4.5
inject inject / to…
47.5%

Source: Official LABBench2 TrialQA leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-5.2 Pro inject / tools,high 93.3% 2,400
GPT-5.2 inject / tools,high 90.8% 2,200
Gemini 3 Pro inject / tools,high 80% 295
Claude Opus 4.6 inject / tools,high 49.2% 1,400
Claude Opus 4.5 inject / tools,high 47.5% 746
Claude Opus 4.6 inject 30% 235
GPT-5.2 Pro inject 26.7% 861
Gemini 3 Pro inject 24.2% 256
GPT-5.2 inject 22.5% 91
Claude Opus 4.5 inject 16.7% 242

Number one over time

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

OpenAI
Own leaderboard Passed 85% in Feb 2026, by GPT-5.2 Pro
GPT-5.2 Pro 93.3%

Source: Official LABBench2 TrialQA leaderboard

GPT-5.2 Pro on the official leaderboard passed 85% in December 2025

Models released before it came out already scored that high. 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%) GPT-5.2 Pro Gemini 3 Pro 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.2 Pro Gemini 3 Pro

Source: Official LABBench2 TrialQA 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 Science and reasoning

All 203 in Science and reasoning
  • GPQA Diamond In use 198 graduate-level 'Google-proof' multiple-choice questions in biology, chemistry and physics. Gemini 4 Carbon 97%
  • Terminal-Bench-Science In use 70 scientific research-workflow tasks across five science areas, run in Harbor containers. Hidden tests give the resolution rate. GPT-6 Astra 68.1%
  • BioMysteryBench In use Bioinformatics problems on anonymized real datasets that require real analysis with tools. Rubric-graded, with human-solvable and human-difficult splits. Claude Fable 5.2 83.7%
  • FrontierScience In use Models solve physics, chemistry, and biology problems in an Olympiad track graded by short answer and a Research track graded by 10-point rubrics. Intern-S2-397B 87%
  • HiPhO In use Models solve theory problems from 2024 and 2025 physics olympiad exams, some with diagrams. Official marking schemes grade answers and steps, mapped to medal levels. Gemini 3 Pro 78.3%
  • LABBench2 In use 11 biology research sub-tasks (literature, figures, tables, patents, trials and more) with tool access. Macro-averaged accuracy. GPT-5.2 60.9%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (5 entries).
  • Pass Models scored 5 models we track.
  • Note Newest score The newest came 9 months ago, in February 2026, for Claude Opus 4.6. That’s expected for a saturated test.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5.2 Pro (#32).
  • Note Headroom Saturated. The best is 93.3%, past 85% since December 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on advances.edisonscientific.com: 10 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.

How we check