[KongchangAI]
BenchmarkScienceAgentBench

ScienceAgentBench

A benchmark for evaluating the performance of scientific agents on scientific tasks.

Timeline (last 90 days)

Nov 10

On ScienceAgentBench, SciMARS + Memory solved 14 of 38 tasks, while the base team solved 11/38.

Unverified50%

All Facts (1)

Source Articles