BioSecBench-RespiratoryVirus-Surveillance V1 (110 evaluations)

Science

Tests whether agents can analyze laboratory results, genetic data and health records to identify respiratory viruses, check how well diagnostic tests work and track how the viruses change and spread. 110 evaluations built from real experimental data, each graded deterministically, with refusals and errors counted as failures. benchmarks.bio excludes it from its overall Capabilities score.

Benchmark source: Benchmarks

Top models (higher is better)

Model	Score	Source
Claude Opus 5.5	25.4	benchmarks.bio V1 published results · benchmarks.bio
Gemini 4 Argon	17.6	benchmarks.bio V1 published results · benchmarks.bio
Claude Sonnet 5.5	17.3	benchmarks.bio V1 published results · benchmarks.bio
Claude Opus 5	14.6	benchmarks.bio V1 published results · benchmarks.bio
GPT-6 Astra	13.3	benchmarks.bio V1 published results · benchmarks.bio
GPT-6.1 Sol	12.4	benchmarks.bio V1 published results · benchmarks.bio
Grok 4.6	11.5	benchmarks.bio V1 published results · benchmarks.bio
GPT-6.1 Terra	11.2	benchmarks.bio V1 published results · benchmarks.bio
GLM-5.3	7.9	benchmarks.bio V1 published results · benchmarks.bio
Kimi K3	7.6	benchmarks.bio V1 published results · benchmarks.bio
Gemini 3.8 Flash	7.3	benchmarks.bio V1 published results · benchmarks.bio
GPT-6 Luna	6.1	benchmarks.bio V1 published results · benchmarks.bio
Mistral Large 4	6.1	benchmarks.bio V1 published results · benchmarks.bio
GPT-5.6 Sol	5.8	benchmarks.bio V1 published results · benchmarks.bio
DeepSeek V4.1 Flash	5.2	benchmarks.bio V1 published results · benchmarks.bio
GPT-5.6 Luna	4.5	benchmarks.bio V1 published results · benchmarks.bio
Nemotron 3.5 Lightning 30B A3B (precision unspecified)	3.9	benchmarks.bio V1 published results · benchmarks.bio