V2 cross-benchmark results

This page reports V2 agentic biology benchmark results from benchmarks.bio. V2 is a clean-v1 rerun on updated evaluation sets and currently covers fewer frontier models than V1, so the two versions are not directly comparable: the V2 overall score requires complete benchmark coverage and weights each benchmark by its configured evaluation count, while V1 equally weights whatever scores are observed. Every benchmark is built from a snapshot of real experimental data captured immediately before a target analysis step, paired with a deterministic grader that checks whether an agent recovered the actual biological result. Results are reported per model and per harness rather than per model alone, because the harness an agent runs under changes its score substantially.

Capabilities

Safeguards