SecureBio
We track 17 benchmarks that SecureBio made or helped make.
0 in use 0 with public code 13 with a leaderboard here
Benchmarks
| Name | Kind | Released | Best score | Status |
|---|---|---|---|---|
| Virology Capabilities Test (VCT) Models answer 322 multimodal virology troubleshooting questions written by expert virologists. Multiple-select variant requires all correct options. | Hazardous knowledge | Apr 2025 | 67.4% | Fading |
| Human Pathogen Capabilities Test Models answer expert-level questions on human pathogens from SecureBio. Scored as accuracy. | Hazardous knowledge | Aug 2025 | 80.7% | System cards only |
| Molecular Biology Capabilities Test Models answer expert-level molecular biology questions from SecureBio. Scored as accuracy. | Genomics and life sciences | 68.7% | System cards only | |
| BioTIER Refuse Models receive 398 dangerous biology prompts. The score measures the percentage correctly refused. | Refusing harmful requests | Sep 2026 | 99.1% | System cards only |
| World-Class Bio Models answer expert-level biology questions in a SecureBio benchmark. Scored as accuracy. | Genomics and life sciences | 68.8% | System cards only | |
| ABC Bench Fragment Design Agents use biology tools to complete a computational genetic-construct design task. One task family of the Agentic Bio-Capabilities Benchmark. | Hazardous knowledge | Jun 2026 |  100% | System cards only |
| ABC Bench Liquid-Handling Robot Agents use biology tools to plan liquid-handling robot steps for a construct-assembly task. One task family of the Agentic Bio-Capabilities Benchmark. | Hazardous knowledge | Jun 2026 | 100% | System cards only |
| SecureBio VMQA, single choice Models answer 350 virology troubleshooting questions in single-choice form. VMQA is an earlier version of the Virology Capabilities Test. | Hazardous knowledge | 61.2% | System cards only | |
| ABC Bench Screening Evasion Agents complete a computational task on nucleic-acid synthesis screening. One task family of the Agentic Bio-Capabilities Benchmark. | Hazardous knowledge | Jun 2026 | 82.9% | System cards only |
| ReproBAIT Agents independently reproduce biological AI models from published scientific papers. Scored as success rate. | Genomics and life sciences | 85% | System cards only | |
| BioTIER Permit Models receive 144 benign biology prompts. The score measures the percentage correctly answered. | Refusing harmful requests | Sep 2026 | 99.9% | System cards only |
| VCT-v2 Models answer an updated set of expert virology troubleshooting questions from SecureBio. Scored as refusal-corrected accuracy. | Lab protocols | Sep 2026 | 60.5% | System cards only |
| Advanced Screening Evasion Models propose strategies to evade DNA synthesis screening and design evading fragments. Scored from 0 to 1 on strategy quality and fragment evasion. | Hazardous knowledge | Sep 2026 | 0.73 | System cards only |
| Virology Capabilities Test (text-only) Models answer the text-only questions of the SecureBio Virology Capabilities Test. Scored as accuracy. | Lab protocols | 46% | System cards only | |
| Human Pathogen Capabilities Test v2 (HPCT v2) Models answer multiple-response questions on a small set of weaponizable pathogens that biosecurity experts rank highest priority. A revised version of HPCT. | Hazardous knowledge | 2026 | 80% | Not in cards |
| Agentic BAIM-LLM Evaluation (ABLE) Agents run a viral-protein redesign workflow. Nine tasks cover structure retrieval, design strategy, tool selection and biological AI model use. Outputs are auto-scored. | Hazardous knowledge | 84.6% | Not in cards | |
| BioTIER Safeguarded model configurations receive harmful and benign biology requests. Scored on refusing requests designated for refusal and allowing benign ones. | Refusing harmful requests | Sep 2026 | Not in cards |