Benchmarks.bio - BioSecBench-Surveillance — leaderboard
Metric: Pass Rate (%). Source: benchmarks.bio. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Grok 4.5 | 53.3 |
| 2 | GPT-5.6 Sol | 52.5 |
| 3 | GPT-5.6 Terra | 51 |
| 4 | GPT-5.6 Luna | 50.3 |
| 5 | GPT-5.5 | 50.2 |
| 6 | Claude Opus 4.8 | 50.2 |
| 7 | Claude Sonnet 5 | 49.8 |
| 8 | Claude Opus 4.7 | 49.6 |
| 9 | Claude Sonnet 4.6 | 48.6 |
| 10 | Gemini 3.5 Flash | 47.1 |
| 11 | Claude Opus 4.6 | 46.7 |
| 12 | Gemini 3.1 Pro (Preview) | 45.3 |
| 13 | GPT-5.4 | 41.3 |
| 14 | Grok 4.3 | 16 |
| 15 | Grok 4.20 Beta (0309) (Reasoning) | 13.7 |
Interactive version: aibenchmarks.dev/benchmark?slug=benchmarks-bio-biosecbench-surveillance · How the rankings work · Data refreshed daily, snapshot 2026-07-16.