List your company

Mathematical Reasoning on AMC 2023 (test) (Accuracy avg@32)

93.8Accuracy (avg@32)NFT
43.04856.22469.482.576May 23, 2025

Evaluation results

MethodLinks
NFTBackbone=Qwen2.5-32B, Fine-tuning Protocol=Supervised fine-tuning2025.0593.8—
RFTBackbone=Qwen2.5-32B, Fine-tuning Protocol=Supervised fine-tuning2025.0592.4—
DAPOBackbone=Qwen2.5-32B, Fine-tuning Protocol=Reinforcement fine-tuning2025.0590.9—
NFTBackbone=Qwen2.5-Math-7B, Fine-tuning Protocol=Supervised fine-tuning2025.0588.5—
DAPOBackbone=Qwen2.5-Math-7B, Fine-tuning Protocol=Reinforcement fine-tuning2025.0585—
DPOBackbone=Qwen2.5-Math-7B, Fine-tuning Protocol=Preference fine-tuning2025.0583.2—
Dr. GRPOBackbone=Qwen2.5-Math-7B, Fine-tuning Protocol=Reinforcement fine-tuning2025.0580.2—
RFTBackbone=Qwen2.5-Math-7B, Fine-tuning Protocol=Supervised fine-tuning2025.0579.7—
GRPOBackbone=Qwen2.5-Math-7B, Fine-tuning Protocol=Reinforcement fine-tuning2025.0579.5—
Qwen2.5-Math-7BBackbone=Qwen2.5-Math-7B, Fine-tuning Protocol=Base2025.0545.8—
Qwen2.5-32BBackbone=Qwen2.5-32B, Fine-tuning Protocol=Base2025.0545—
GRPOBackbone=Qwen3-1.7B, Training Step Selection=Last (Step 400)2026.06—46.7
GRPOBackbone=Qwen3-1.7B, Training Step Selection=Best (Peak)2026.06—46.7
OPCDBackbone=Qwen3-1.7B, Training Step Selection=Last (Step 400)2026.06—24.5
OPCDBackbone=Qwen3-1.7B, Training Step Selection=Best (Peak)2026.06—47.4
RLSDBackbone=Qwen3-1.7B, Training Step Selection=Last (Step 400)2026.06—57.3
RLSDBackbone=Qwen3-1.7B, Training Step Selection=Best (Peak)2026.06—58.2
SDPG-UFKLBackbone=Qwen3-1.7B, Training Step Selection=Last (Step 400)2026.06—63.7
SDPG-UFKLBackbone=Qwen3-1.7B, Training Step Selection=Best (Peak)2026.06—66.6
SDPG-URKLBackbone=Qwen3-1.7B, Training Step Selection=Last (Step 400)2026.06—62
SDPG-URKLBackbone=Qwen3-1.7B, Training Step Selection=Best (Peak)2026.06—62