List your company

Tool-use API Generalization on ToolBench G1 v1

83.5Pass RateEVOTOOL
45.64455.47265.375.128Mar 5, 2026

Evaluation results

MethodLinks
EVOTOOLBackbone=GPT-4o, Optimization Strategy=Ours2026.0383.5
DRAFTBackbone=GPT-4o, Optimization Strategy=Single-aspect optimization2026.0382.1
EASYTOOLBackbone=GPT-4o, Optimization Strategy=Single-aspect optimization2026.0380.3
EVOTOOLBackbone=Qwen3-8B, Optimization Strategy=Ours2026.0373.5
ANYTOOLBackbone=GPT-4o, Optimization Strategy=Single-aspect optimization2026.0373.3
DRAFTBackbone=Qwen3-8B, Optimization Strategy=Single-aspect optimization2026.0372.2
EASYTOOLBackbone=Qwen3-8B, Optimization Strategy=Single-aspect optimization2026.0370.7
EvoPromptBackbone=GPT-4o, Optimization Strategy=Monolithic optimization2026.0370.1
OPROBackbone=GPT-4o, Optimization Strategy=Monolithic optimization2026.0369.3
PromptBreederBackbone=GPT-4o, Optimization Strategy=Monolithic optimization2026.0368.5
ReActBackbone=GPT-4o, Optimization Strategy=Hand-crafted policies2026.0368.2
ANYTOOLBackbone=Qwen3-8B, Optimization Strategy=Single-aspect optimization2026.0364.5
Plan-and-SolveBackbone=GPT-4o, Optimization Strategy=Hand-crafted policies2026.0363.3
AdaPlannerBackbone=GPT-4o, Optimization Strategy=Single-aspect optimization2026.0362.2
EvoPromptBackbone=Qwen3-8B, Optimization Strategy=Monolithic optimization2026.0361.7
OPROBackbone=Qwen3-8B, Optimization Strategy=Monolithic optimization2026.0361
PromptBreederBackbone=Qwen3-8B, Optimization Strategy=Monolithic optimization2026.0360.3
ReActBackbone=Qwen3-8B, Optimization Strategy=Hand-crafted policies2026.0360
Plan-and-SolveBackbone=Qwen3-8B, Optimization Strategy=Hand-crafted policies2026.0355.7
AdaPlannerBackbone=Qwen3-8B, Optimization Strategy=Single-aspect optimization2026.0354.7
CoTBackbone=GPT-4o, Optimization Strategy=Hand-crafted policies2026.0353.5
CoTBackbone=Qwen3-8B, Optimization Strategy=Hand-crafted policies2026.0347.1