List your company
ResearchFormerly WizWand

Mathematical Reasoning on AMC23 (Avg@k, Pass@k)

62.19Avg@kRPSFT
17.823629.341840.8652.3782May 8, 2026
Updated 5mo ago

Evaluation results

MethodLinks
RPSFTBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=DAPO2026.0562.1995
IWBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=DAPO2026.056092.5
SFTBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=DAPO2026.0558.1290
RPSFTBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=init2026.0555.3190
DFTBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=DAPO2026.0553.1382.5
IWBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=init2026.0552.585
SFTBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=init2026.0550.4787.5
DFTBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=init2026.0548.9182.5
IWBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=DAPO2026.0540.9485
RPSFTBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=DAPO2026.054082.5
DFTBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=DAPO2026.0539.5372.5
SFTBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=DAPO2026.0537.575
IWBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=init2026.0536.2582.5
SFTBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=init2026.053582.5
RPSFTBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=init2026.0534.8480
SFTBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=DAPO2026.0534.3882.5
DFTBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=init2026.0534.0677.5
IWBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=init2026.0533.5980
RPSFTBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=DAPO2026.0533.5985
IWBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=DAPO2026.0532.8177.5
SFTBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=init2026.0532.1977.5
RPSFTBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=init2026.0531.5685
DFTBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=DAPO2026.0524.5360
DFTBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=init2026.0519.5362.5