# BioSecBench-RespiratoryVirus-Countermeasures results Compare current model-and-harness results for BioSecBench-RespiratoryVirus-Countermeasures. Tests whether AI agents can analyze biological data, laboratory results, and patient records to understand how respiratory viruses cause illness, how immunity protects people, and whether vaccines and treatments remain effective as viruses change. These capabilities support research on preventing infections and reducing severe disease. Scores show the share of attempts that reach the correct answer, counting refusals and errors as failures. A higher score means the model is more accurate at these tasks. Current V1 covers 64 evaluations and 30 ranked configurations. Data updated 2026-11-13. The highest-ranked published configurations are Claude Fable 5.2* (Pi, LSVP, 33.3%); Claude Fable 5.2* (Claude Code, LSVP, 32.3%); Gemini 4 Carbon (Pi, 30.2%). The highest-ranked published run without an LSVP exemption is Gemini 4 Carbon (Pi, 30.2%). Scores report benchmark-specific biological task performance on a 0–100 percentage scale. See the linked paper and repository for task construction, grading and uncertainty methodology. Results describe the complete model and agent harness used for each run, and are not comparable across different benchmarks or evaluation versions. Data updated: 2026-11-13 (November 13, 2026) Artifact generated: 2026-11-13T18:24:13.104Z - Domain: Biosecurity - Horizon: short - Assessment: Capabilities - Published score scope: Current V1 evaluation set (64 evaluations) Scores use a 0–100 percentage scale. Consult the repository and paper for benchmark-specific task construction, grading, aggregation, and uncertainty methodology. Results compare model-and-harness combinations. LSVP: Anthropic's safety-filter-exempt evaluation variant, which produces fewer refusals on biology prompts. LSVP results are reported alongside the model's standard run and are not a replacement for it. | Rank | Model | Harness | Provider | Score | Variant | | ---: | --- | --- | --- | ---: | --- | | 1 | Claude Fable 5.2* | Pi | Anthropic | 33.3% | LSVP | | 2 | Claude Fable 5.2* | Claude Code | Anthropic | 32.3% | LSVP | | 3 | Gemini 4 Carbon | Pi | Google | 30.2% | | | 4 | Claude Opus 5.5* | Pi | Anthropic | 27.1% | LSVP | | 5 | Claude Opus 5.5* | Claude Code | Anthropic | 25.5% | LSVP | | 6 | Claude Sonnet 5.5 | Pi | Anthropic | 18.8% | | | 7 | Claude Sonnet 5.5* | Pi | Anthropic | 18.8% | LSVP | | 8 | Claude Sonnet 5.5* | Claude Code | Anthropic | 18.2% | LSVP | | 9 | Claude Fable 5.2 | Claude Code | Anthropic | 17.7% | | | 10 | Claude Fable 5.2 | Pi | Anthropic | 16.9% | | | 11 | Claude Sonnet 5.5 | Claude Code | Anthropic | 16.7% | | | 12 | GPT-6 Astra | Pi | OpenAI | 13.5% | | | 13 | Claude Opus 5.5 | Claude Code | Anthropic | 13.0% | | | 14 | Claude Opus 5.5 | Pi | Anthropic | 12.0% | | | 15 | Claude Opus 5* | Claude Code | Anthropic | 12.0% | LSVP | | 16 | Claude Opus 5* | Pi | Anthropic | 12.0% | LSVP | | 17 | Gemini 4 Argon | Pi | Google | 12.0% | | | 18 | GPT-6.1 Terra | Pi | OpenAI | 11.5% | | | 19 | Grok 4.7 | Pi | SpaceXAI | 11.5% | | | 20 | GPT-6.1 Sol | Pi | OpenAI | 10.9% | | | 21 | GPT-6 Astra | Codex | OpenAI | 9.9% | | | 22 | Grok 4.6 | Pi | SpaceXAI | 9.4% | | | 23 | DeepSeek V4.1 Flash | Pi | DeepSeek | 6.3% | | | 24 | GLM 5.3 | Pi | Z.ai | 6.3% | | | 25 | Mistral Large 4.0 | Pi | Mistral | 4.2% | | | 26 | Gemini 3.8 Flash | Pi | Google | 2.6% | | | 27 | GPT-6 Luna | Pi | OpenAI | 2.1% | | | 28 | Kimi K3.1 Pro | Pi | Moonshot | 1.6% | | | 29 | Nemotron 3 Ultra 550B A55B | Pi | NVIDIA | 1.0% | | | 30 | Nemotron 3.5 Lightning | Pi | NVIDIA | 0.0% | | ## Sources and downloads - [Paper PDF](/papers/respcounter.pdf) - [Original publication](https://latch.bio/respvirus-countermeasures) - [Repository](https://github.com/latchbio/biosecbench-respvirus-countermeasures) - [Interactive benchmark](https://benchmarks.bio/respvirus-countermeasures) - [JSON](https://benchmarks.bio/benchmarks/biosecbench-respvirus-countermeasures/latest.json) - [CSV](https://benchmarks.bio/benchmarks/biosecbench-respvirus-countermeasures/latest.csv) - [Current V1 cross-benchmark leaderboard](https://benchmarks.bio/results/v1/)