LABBench2 SourceQuality
Models assess the quality of scientific information sources.
The publisher reports model results for this evaluation.
- Kind
- Research science
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Subject
- Biological sciences
- Language
- English
- Interaction
- Single turn
- Refresh
- New versions replace it
- Run by
- A host
- Based on
- LABBench2
- In views
- Biology and medicine
- Strongest model tested
- GPT-5.2 Pro #32 on the capability index
- Last model added
- February 2026
- Scores refreshed
- November 20th, 2026
Gemini 3 Pro leads with 90% 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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1
Gemini 3 Pro code,high / file 90%
- 2 GPT-5.2 Pro file 80.7%
- 3 GPT-5.2 file 79.3%
- 4 Claude Opus 4.6 code,high / file 67.3%
- 5 Claude Opus 4.5 file 66%
Source: Official LABBench2 SourceQuality leaderboard
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | | 90% | code,high / file | Nov 2025 | Mar 2026 | Official leaderboard |
| 2 | GPT-5.2 Pro | 80.7% | file | Dec 2025 | Mar 2026 | Official leaderboard |
| 3 | GPT-5.2 | 79.3% | file | Dec 2025 | Mar 2026 | Official leaderboard |
| 4 | Claude Opus 4.6 | 67.3% | code,high / file | Feb 2026 | Mar 2026 | Official leaderboard |
| 5 | Claude Opus 4.5 | 66% | file | 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.
Source: Official LABBench2 SourceQuality leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| code,high / file | 90% | 256 | |||
| file | 88.7% | 238 | |||
| GPT-5.2 Pro | file | 80.7% | 480 | ||
| GPT-5.2 | file | 79.3% | 163 | ||
| GPT-5.2 Pro | code,high / file | 76% | 923 | ||
| GPT-5.2 | code,high / file | 72% | 3,500 | ||
| Claude Opus 4.6 | code,high / file | 67.3% | 1,900 | ||
| Claude Opus 4.5 | file | 66% | 326 | ||
| Claude Opus 4.5 | code,high / file | 62% | 1,100 | ||
| Claude Opus 4.6 | file | 60.7% | 261 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official LABBench2 SourceQuality leaderboard
Gemini 3 Pro on the official leaderboard passed 85% in November 2025
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official LABBench2 SourceQuality 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
- 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 90%, past 85% since November 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.