List your company

Sequential Tool Use on RestBench Spotify (Success Rate)

86.1Success RateEVOTOOL
52.71661.38370.0578.717Mar 5, 2026

Evaluation results

MethodLinks
EVOTOOLBackbone=GPT-4o2026.0386.1
DRAFTBackbone=GPT-4o2026.0385.2
EASYTOOLBackbone=GPT-4o2026.0383.5
ANYTOOLBackbone=GPT-4o2026.0378.4
EvoPromptBackbone=GPT-4o2026.0377.4
OPROBackbone=GPT-4o2026.0376.4
PromptBreederBackbone=GPT-4o2026.0375.2
ReActBackbone=GPT-4o2026.0374.3
EVOTOOLBackbone=Qwen3-8B2026.0373.2
DRAFTBackbone=Qwen3-8B2026.0372.4
AdaPlannerBackbone=GPT-4o2026.0370.1
Plan-and-SolveBackbone=GPT-4o2026.0369.2
EASYTOOLBackbone=Qwen3-8B2026.0368
ANYTOOLBackbone=Qwen3-8B2026.0366.6
EvoPromptBackbone=Qwen3-8B2026.0365.8
OPROBackbone=Qwen3-8B2026.0364.9
PromptBreederBackbone=Qwen3-8B2026.0363.9
CoTBackbone=GPT-4o2026.0363.5
ReActBackbone=Qwen3-8B2026.0363.2
AdaPlannerBackbone=Qwen3-8B2026.0359.6
Plan-and-SolveBackbone=Qwen3-8B2026.0358.8
CoTBackbone=Qwen3-8B2026.0354