[KongchangAI]
BenchmarkAutonomous Science Bench

Autonomous Science Bench

A benchmark for evaluating scientific discovery capabilities, potentially involving multiple models and tasks.

Timeline (last 90 days)

Nov 10

On Autonomous Science Bench, SciMARS + Memory solved 12 of 18 GPT-6-Astra attempts, while the base multi-agent team solved only 8/18.

Unverified50%
Nov 10

On Autonomous Science Bench, SciMARS + Memory solved 2 of 18 GLM-5.3 attempts, while the base multi-agent team solved only 1/18.

Unverified50%

All Facts (2)

Source Articles