Benchmarks

Terminal-Bench Science 0.1

Agentsunit % · normalized over [0, 70]

Terminal-Bench-Science 0.1 — a Stanford-led set of 70 agentic scientific workflows (life, physical, earth, mathematical and engineering sciences) executed in a terminal: read data, run computations, submit results. Standard error is roughly +/-3.5-4.5 points per model.

#ModelSourceScoreNormalized

Score distribution

5 tracked results across the normalization window

070

Score vs. parameters

Open-weights models, log-x params

No open-weights models with disclosed parameter counts have a score here yet.