Expert comparisons on biothreat information
PhD biology experts compare model answers to expert answers on long-form biorisk questions. Scored as win rate on accuracy, understanding and ease of execution.
OpenAI Preparedness evaluation. Results are reported per dimension for pre-mitigation models.
- Made by
- OpenAI
- Released
- September 2024
- Kind
- Hazardous knowledge
- Level
- Expert
- Scored
- Graded by people
- Answers
- Open-ended
- Tasks
- Kept private
- Last in a system card
- January 2025
- Last model added
- January 2025
4
System cards report it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for Expert comparisons on biothreat information yet.
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.
4 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Jan 31, 2025 | o3-mini system card | Expert comparisons, win rates shown for pre-mitigation models only (5.4.2) | Bio and chem risk | |
| Dec 5, 2024 | o1 system card | Expert Human Preference Win Rates, o1 (pre-mitigation) 75.0% accuracy, 68.7% understanding, 80.5% ease of execution, no overall score (5.5.2) | Bio and chem risk | |
| Sep 12, 2024 | o1-preview system card | Expert comparisons win rates, o1-preview (pre-mitigation) 72.4% accuracy, 69.5% understanding, 74.3% ease of execution, no overall score (4.3.2) | Bio and chem risk | |
| Sep 12, 2024 | o1-mini system card | Expert comparisons win rates, o1-mini (pre-mitigation) 67.4% accuracy, 50.6% understanding, 79.6% ease of execution, no overall score (4.3.2) | Bio and chem risk |
More in Biology and chemistry
- GeneBench Pro In use Agents analyze messy simulated genomics and biology datasets to estimate a decision-relevant quantity across 129 problems. Scored automatically against known answers. GPT-5.6 Sol 31.5%
- SUPERChem In use Models solve 500 expert-written chemistry reasoning problems, offered in multimodal and text-only forms. Expert solution paths also allow a reasoning path score.
Tencent Hy4 preview 66.4% - LifeSciBench In use Models complete 750 expert-written life science research tasks, often with attached figures, tables, or sequence files. Graded against expert rubrics as score and pass rate. GPT-Rosalind-6 61.3%
- MedChemBench (OpenAI) In use Models answer chemistry questions from an OpenAI internal set, grouped with OpenAI's life science research evaluations. OpenAI has not published the task format. GPT-Rosalind-6 49.6%
- ProtocolQA Open-Ended In use Models correct errors in published lab protocols using open-ended questions adapted from LAB-Bench ProtocolQA. Scored as pass@1. GPT-6 Cyber 47.2%
- MolecularIQ In use Models answer questions about molecular graphs, such as counting, indexing and constrained generation, and a symbolic checker verifies each answer. gpt-oss-120b 47.5%