Benchmarks.bio - BioSecBench-Function: leaderboard
BioSecBench-Function (benchmarks.bio) — genomic function prediction under biosecurity framing: agentic tasks that ask a model to reason from sequence to function across 111 evaluations, scored as pass rate over gradeable trials with refusals reported separately.
Metric: Pass Rate (%). Source: benchmarks.bio. Saturation forecast: Around 2028. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 | 50.3 | #12 |
| 2 | GPT-6 Astra | 48.6 | #6 |
| 3 | Claude Opus 4.8 | 44.6 | #37 |
| 4 | Grok 4.6 | 44.1 | #26 |
| 5 | Gemini 3.5 Flash | 42.2 | #60 |
| 6 | Gemini 3.7 Flash | 40.1 | #23 |
| 7 | DeepSeek V4.1 Flash | 38.7 | #36 |
| 8 | GPT-5.6 Sol | 38.3 | #19 |
| 9 | Claude Sonnet 5 | 37.2 | #57 |
| 10 | GPT-5.5 | 36.5 | #31 |
| 11 | Grok 4.5 | 35.6 | #48 |
| 12 | GPT-5.6 Terra | 33.5 | #41 |
| 13 | GPT-5.6 Luna | 26.9 | #68 |
No result here: #3 Claude Opus 5.5, #7 GPT-6.1 Sol, #8 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=benchmarks-bio-biosecbench-function · How It Works · Data refreshed daily, snapshot 2026-10-20.