List your company

Tool Learning on RestBench TMDB

86.2Success RateEVOTOOL
29.83244.46659.173.734Feb 17, 2025May 6, 2025Jul 23, 2025Oct 9, 2025Dec 26, 2025Mar 14, 2026Jun 1, 2026

Evaluation results

MethodLinks
EVOTOOLBackbone=GPT-4o2026.0386.2——
ToolCoderBackbone=gpt-4o-mini, Paradigm=Code-based2025.02857883
DRAFTBackbone=GPT-4o2026.0384.3——
RestGPTBackbone=gpt-4o-mini, Paradigm=Text-based2025.02833349
ToolCoder w/o Reusable RepositoryBackbone=gpt-4o-mini, Paradigm=Code-based, Reusable Repository=false2025.02837178
EASYTOOLBackbone=GPT-4o2026.0381.4——
CodeActBackbone=gpt-4o-mini, Paradigm=Code-based2025.02805667
HarnessForgeBackbone=Qwen3-8B2026.0680—88.75
ATCBackbone=gpt-4o-mini, Paradigm=Code-based2025.02785862
EvoPromptBackbone=GPT-4o2026.0376.3——
ReActBackbone=gpt-4o-mini, Paradigm=Text-based2025.02764850
HarnessForgeBackbone=Qwen3-4B2026.0676—85.1
EVOTOOLBackbone=Qwen3-8B2026.0375.9——
ANYTOOLBackbone=GPT-4o2026.0375.2——
ChameleonBackbone=gpt-4o-mini, Paradigm=Text-based2025.02754552
EasyToolBackbone=gpt-4o-mini, Paradigm=Text-based2025.02754562
ToolCoder w/o Error ReflectionBackbone=gpt-4o-mini, Paradigm=Code-based, Error Reflection=false2025.02756577
DRAFTBackbone=Qwen3-8B2026.0374.2——
PromptBreederBackbone=GPT-4o2026.0374.1——
RLOOBackbone=Qwen3-8B2026.0674—84.25
OPROBackbone=GPT-4o2026.0373.8——
ReActBackbone=GPT-4o2026.0372.4——
ConAgentsBackbone=gpt-4o-mini, Paradigm=Text-based2025.02723857
EASYTOOLBackbone=Qwen3-8B2026.0371.6——
GRPOBackbone=Qwen3-8B2026.0670—83.2
SFTBackbone=Qwen3-8B2026.0669—82.92
EvoPromptBackbone=Qwen3-8B2026.0367.1——
AdaPlannerBackbone=GPT-4o2026.0366.2——
ANYTOOLBackbone=Qwen3-8B2026.0366.2——
PromptBreederBackbone=Qwen3-8B2026.0365.2——
OPROBackbone=Qwen3-8B2026.0364.9——
Plan-and-SolveBackbone=GPT-4o2026.0364.8——
GRPOBackbone=Qwen3-4B2026.0664—76.67
ReActBackbone=Qwen3-8B2026.0363.7——
SFTBackbone=Qwen3-4B2026.0661—75.7
RLOOBackbone=Qwen3-4B2026.0661—77.42
CoTBackbone=GPT-4o2026.0359.8——
AdaPlannerBackbone=Qwen3-8B2026.0358.3——
Plan-and-SolveBackbone=Qwen3-8B2026.0357——
CoTBackbone=Qwen3-8B2026.0352.6——
ADASBackbone=Qwen3-8B2026.0651—60.41
MermaidFlowBackbone=Qwen3-8B2026.0647—58.67
ADASBackbone=Qwen3-4B2026.0645—57.43
MaASBackbone=Qwen3-8B2026.0643—54.78
MermaidFlowBackbone=Qwen3-4B2026.0639—51.95
AFlowBackbone=Qwen3-8B2026.0639—51.28
AgentSquareBackbone=Qwen3-8B2026.0638—53.83
MaASBackbone=Qwen3-4B2026.0637—46.57
AgentSquareBackbone=Qwen3-4B2026.0635—49.83
AFlowBackbone=Qwen3-4B2026.0632—47.64