Benchmark
Agent Tech
An agent benchmark oriented toward scientific research workflows, assessing a model's planning and execution capabilities across multi-step scientific tasks such as literature retrieval, experimental design, and data analysis.
Timeline (last 90 days)
Nov 12
On the Agent Tech scientific research benchmark, Fable 5.2 scored 74.6%, Opus 5.5 scored 58.7%, Astra scored 68.1%, and Carbon scored 64.8%.
Unverified50%