List your company

Chain-of-Thought Reasoning on CoT-Collection

73.7Composite ScoreSFT-Tag
30.248841.529452.8164.0906Dec 24, 2025

Evaluation results

MethodLinks
SFT-TagModel=Qwen2.5-7B2025.1273.7
SFT(baseline)Model=Qwen2.5-7B2025.1273.48
SFTKey-TagModel=Qwen2.5-7B2025.1273.42
SFTKey-TagModel=Qwen3-8B-Base2025.1272.98
SFT(baseline)Model=Qwen3-8B-Base2025.1272.78
SFT-TagModel=Qwen3-8B-Base2025.1272.64
Key-TagModel=Qwen3-8B-Base2025.1269.21
SFTKey-TagModel=SmolLM3-3B-Base2025.1267.97
SFT(baseline)Model=SmolLM3-3B-Base2025.1266.78
SFT-TagModel=SmolLM3-3B-Base2025.1265.02
Key-TagModel=Qwen2.5-7B2025.1244.8
SFTKey-TagModel=Qwen2.5-3B2025.1239.97
SFT-TagModel=Qwen2.5-3B2025.1237.52
SFT(baseline)Model=Qwen2.5-3B2025.1237.24
Key-TagModel=SmolLM3-3B-Base2025.1236.94
Key-TagModel=Qwen2.5-3B2025.1234.3
Key-TagModel=Qwen2.5-1.5B2025.1234.3
SFT-TagModel=Qwen2.5-1.5B2025.1233.32
SFT(baseline)Model=Qwen2.5-1.5B2025.1232.48
SFTKey-TagModel=Qwen2.5-1.5B2025.1231.92