List your company

Mathematical Reasoning on OpenR1 Math 220k

0.8633Composite ScoreSFTKey-Tag
0.2421080.4033790.564650.725921Dec 24, 2025

Evaluation results

MethodLinks
SFTKey-TagModel=Qwen3-8B-Base2025.120.8633
SFTKey-TagModel=Qwen2.5-7B2025.120.7217
SFT-TagModel=Qwen3-8B-Base2025.120.6959
SFT(baseline)Model=Qwen3-8B-Base2025.120.6164
Key-TagModel=Qwen3-8B-Base2025.120.5831
SFT(baseline)Model=Qwen2.5-7B2025.120.5772
SFT-TagModel=SmolLM3-3B-Base2025.120.5645
SFT-TagModel=Qwen2.5-7B2025.120.5604
SFTKey-TagModel=SmolLM3-3B-Base2025.120.5225
SFT(baseline)Model=SmolLM3-3B-Base2025.120.4574
Key-TagModel=Qwen2.5-7B2025.120.3822
Key-TagModel=Qwen2.5-3B2025.120.357
SFTKey-TagModel=Qwen2.5-1.5B2025.120.3434
SFTKey-TagModel=Qwen2.5-3B2025.120.3416
SFT-TagModel=Qwen2.5-3B2025.120.3402
SFT(baseline)Model=Qwen2.5-3B2025.120.3094
SFT(baseline)Model=Qwen2.5-1.5B2025.120.2842
Key-TagModel=Qwen2.5-1.5B2025.120.2828
SFT-TagModel=Qwen2.5-1.5B2025.120.28
Key-TagModel=SmolLM3-3B-Base2025.120.266