List your company

Multi-Turn Tool-Integrated Reasoning (TIR) on AIME24 (Peak avg@32 score)

41.46Peak avg@32 scoreOTB
24.341628.785833.2337.6742Feb 6, 2026

Evaluation results

MethodLinks
OTBBackbone=Qwen2.5-7B, Reasoning Paradigm=TIR2026.0241.46
SimpleTIRBackbone=Qwen2.5-7B, Reasoning Paradigm=TIR2026.0237.91
OGBBackbone=Qwen2.5-7B, Reasoning Paradigm=TIR2026.0230.63
OPOBackbone=Qwen2.5-7B, Reasoning Paradigm=TIR2026.0229.9
GRPOBackbone=Qwen2.5-7B, Reasoning Paradigm=TIR2026.0227.6
RLOOBackbone=Qwen2.5-7B, Reasoning Paradigm=TIR2026.0225