Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Agentic Task Success on ScienceWorld full (val)

26.7Success Rate

TREK (DeepSeek-V4)

11.93215.76619.623.434Jul 6, 2026
Updated 19d ago

Evaluation Results

MethodLinks
2026.07
26.7
2026.07
23.4
2026.07
21.6
2026.07
12.5