List your company

Multi-Turn Tool-Integrated Reasoning (TIR) on AMC23

79.45Peak avg@32 ScoreOTB
58.6564.0569.4574.85Feb 6, 2026

Evaluation results

MethodLinks
OTBBackbone=Qwen2.5-7B, Reasoning Paradigm=TIR2026.0279.45
SimpleTIRBackbone=Qwen2.5-7B, Reasoning Paradigm=TIR2026.0271.25
OPOBackbone=Qwen2.5-7B, Reasoning Paradigm=TIR2026.0264.84
OGBBackbone=Qwen2.5-7B, Reasoning Paradigm=TIR2026.0262.5
RLOOBackbone=Qwen2.5-7B, Reasoning Paradigm=TIR2026.0262.42
GRPOBackbone=Qwen2.5-7B, Reasoning Paradigm=TIR2026.0259.45