BioSecBench-Refusal C
AI benchmark · Safety
What is BioSecBench-Refusal?
Paired agentic biosecurity benchmark measuring both excessive refusal on legitimate scientific work and refusal of concealed biosecurity hazards. It contains 61 Routine and 46 Red-Team evaluations and uses direct and meta framings. The public release provides aggregate model-by-harness results; the full task set, hazard-bearing data, ground-truth rationales, and agent trajectories remain restricted by the publisher.
Tier C
Niche: a handful of models scored, or built by an RL vendor.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 10 models scored
- in curated RL directories (1 pt)
How we got to tier C
- Adoption: 10 models scored. Tier C.
- Not yet read on X.
- In curated RL directories: 1 point, a floor of none.
- Not yet confirmed by a line from its own site or paper.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Not on the map yet: no line from its own site or paper places it in a domain.
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-11 snapshot.