List your company

Question Answering on OpenBookQA (Composite Score)

92.14Composite ScoreSFTKey-Tag
43.488856.119468.7581.3806Dec 24, 2025

Evaluation results

MethodLinks
SFTKey-TagModel=Qwen2.5-7B2025.1292.14
SFT-TagModel=Qwen3-8B-Base2025.1290.62
SFT(baseline)Model=Qwen3-8B-Base2025.1290.2
SFTKey-TagModel=Qwen3-8B-Base2025.1290.2
SFT-TagModel=Qwen2.5-7B2025.1289.92
SFT(baseline)Model=Qwen2.5-7B2025.1289.22
Key-TagModel=Qwen3-8B-Base2025.1287.62
SFT(baseline)Model=SmolLM3-3B-Base2025.1285.16
SFTKey-TagModel=SmolLM3-3B-Base2025.1282
SFT-TagModel=SmolLM3-3B-Base2025.1271.34
Key-TagModel=Qwen2.5-7B2025.1262.72
Key-TagModel=SmolLM3-3B-Base2025.1261.92
Key-TagModel=Qwen2.5-1.5B2025.1258.66
SFT-TagModel=Qwen2.5-1.5B2025.1257.54
Key-TagModel=Qwen2.5-3B2025.1255.3
SFTKey-TagModel=Qwen2.5-1.5B2025.1252.08
SFT(baseline)Model=Qwen2.5-3B2025.1251.38
SFT-TagModel=Qwen2.5-3B2025.1249.84
SFTKey-TagModel=Qwen2.5-3B2025.1249.7
SFT(baseline)Model=Qwen2.5-1.5B2025.1245.36