List your company

Functional Tool-Use on Simulation Benchmark unseen tools

30SR (Scoop S01)FORGE
-1.26.91523.1Jul 7, 2026

Evaluation results

MethodLinks
FORGE2026.0730306742232323235320534236
DP2026.07131327180131083323232617
ATM2026.0713177121007677368
FM2026.07031770733131717169