List your company

Tool-use API Generalization on ToolBench G3

71.5Pass RateEVOTOOL
38.42847.01455.664.186Mar 5, 2026

Evaluation results

MethodLinks
EVOTOOLBackbone=GPT-4o2026.0371.5
DRAFTBackbone=GPT-4o2026.0368.4
EASYTOOLBackbone=GPT-4o2026.0366.2
ANYTOOLBackbone=GPT-4o2026.0361
EvoPromptBackbone=GPT-4o2026.0359.2
OPROBackbone=GPT-4o2026.0358.9
EVOTOOLBackbone=Qwen3-8B2026.0358.6
ReActBackbone=GPT-4o2026.0357.9
DRAFTBackbone=Qwen3-8B2026.0356.1
Plan-and-SolveBackbone=GPT-4o2026.0355.3
PromptBreederBackbone=GPT-4o2026.0354.7
EASYTOOLBackbone=Qwen3-8B2026.0354.3
ANYTOOLBackbone=Qwen3-8B2026.0350
AdaPlannerBackbone=GPT-4o2026.0348.8
EvoPromptBackbone=Qwen3-8B2026.0348.5
CoTBackbone=GPT-4o2026.0348.4
OPROBackbone=Qwen3-8B2026.0348.3
ReActBackbone=Qwen3-8B2026.0347.5
Plan-and-SolveBackbone=Qwen3-8B2026.0345.3
PromptBreederBackbone=Qwen3-8B2026.0344.9
AdaPlannerBackbone=Qwen3-8B2026.0340
CoTBackbone=Qwen3-8B2026.0339.7