BioSecBench-Surveillance (Claude Code): leaderboard
BioSecBench-Surveillance (LatchBio, 2026) gives an agent raw pathogen sequencing data and asks for a surveillance result, such as a lineage, a resistance profile or a source, graded deterministically against held-out ground truth over 100 restricted evaluations. This board is the endpoint pass rate under Claude Code: each evaluation's share of passing runs (three runs each, refused runs left out of the denominator), averaged over evaluations, in percent. Higher is better.
Metric: Endpoint pass rate (%). Source: github.com. Saturation forecast: Around August 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 46.7 | #100 |
| 2 | Claude Opus 4.7 | 44.2 | #75 |
| 3 | Claude Sonnet 4.6 | 43.6 | #158 |
| 4 | Claude Opus 4.8 | 39.5 | #56 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=biosecbench-surveillance-claude-code · How It Works · Data refreshed daily, snapshot 2026-11-12.