Observed arrival · 2026-11-13
FrontierBioML’s computational-biology agent leaderboard
A benchmark site presenting results from evaluations of agents on computational-biology tasks.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Researchers comparing computational-biology agents
- Worth noticing
- The leaderboard pairs mean scores and run counts with 95% intervals, average cost, and score-versus-time views.
Field notes
Readers can change the displayed outcome among score, outcomes, and results without refusals, then inspect score-versus-time and per-task views. The page groups example tasks into categories and provides a citation section with a BibTeX copy control. A separate Method link leads to the evaluation description; the extracted homepage does not show the full task prompts or protocol.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
◎NicheUnusually specific use
One card from the complete issue