benchmarks.bio

Biosecurity · Capabilities

BioSecBench-Surveillance results

Biosecurity surveillance tasks that measure an agent's ability to analyze biological threat signals.

Published score: Full benchmark (102 evaluations) · short horizon · data updated 2026-09-20

Published BioSecBench-Surveillance scores
RankModelHarnessProviderScore
1Claude Opus 5PiAnthropic51.5%
2GPT-6 AstraPiOpenAI48.5%
3Grok 4.6Grok BuildSpaceXAI48.0%
4Grok 4.6PiSpaceXAI47.5%
5Claude Opus 5Claude CodeAnthropic43.6%
6GPT-6 AstraCodexOpenAI35.2%

Methodology and provenance

Scores use a 0–100 percentage scale. See the benchmark repository, hosted paper PDF, and original publication for task construction, grading, aggregation, and uncertainty details.