List your company
ResearchFormerly WizWand

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

46.78Avg@kRPSFT
16.235224.165132.09540.0249May 8, 2026
Updated 5mo ago

Evaluation results

MethodLinks
RPSFTBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=DAPO2026.0546.7861.78
SFTBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=DAPO2026.0543.4459.55
IWBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=DAPO2026.0542.9658.81
IWBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=init2026.0539.1856.3
RPSFTBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=init2026.053856.15
SFTBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=init2026.0537.4154.96
DFTBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=init2026.0537.4150.07
DFTBackbone=Qwen2.5-7B-Instruct, RL Fine-tuning Stage=DAPO2026.0536.8148.59
RPSFTBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=DAPO2026.0529.0446.67
RPSFTBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=init2026.0527.6743.85
IWBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=DAPO2026.0527.5942.66
SFTBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=DAPO2026.0527.4444.44
RPSFTBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=DAPO2026.0527.0343.7
SFTBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=init2026.0526.2542.37
DFTBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=init2026.0526.2226.22
IWBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=init2026.052642.67
IWBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=init2026.0525.7141.63
SFTBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=init2026.0525.5941.33
SFTBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=DAPO2026.0525.5642.07
RPSFTBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=init2026.0525.5242.22
IWBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=DAPO2026.0525.4441.93
DFTBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=DAPO2026.0525.336.89
DFTBackbone=Qwen2.5-3B-Instruct, RL Fine-tuning Stage=init2026.052538.37
DFTBackbone=Llama-3.1-8B-Instruct, RL Fine-tuning Stage=DAPO2026.0517.4128.44