List your company
ResearchFormerly WizWand

General Language Understanding on 7-Task Evaluation Suite (test)

75.7Average AccuracyFP16
52.358.37564.4570.525Jul 1, 2026
Updated 4mo ago

Evaluation results

MethodLinks
FP16Base Model=Qwen2.5-7B, Bits=16.02026.0775.7
TASA b3.5Base Model=Qwen2.5-7B, Bits=3.5, Calibration Data (Calib)=Mixed2026.0774.1
FP16Base Model=LLaMA-3-8B, Bits=16.02026.0770.9
TASA b3.0Base Model=Qwen2.5-7B, Bits=3.0, Calibration Data (Calib)=Mixed2026.0769.5
TASA b3.5Base Model=LLaMA-3-8B, Bits=3.5, Calibration Data (Calib)=Mixed2026.0768.9
TASA b3.0Base Model=LLaMA-3-8B, Bits=3.0, Calibration Data (Calib)=Mixed2026.0766.4
GPTQBase Model=Qwen2.5-7B, Bits=3.0, Calibration Data (Calib)=Wiki2026.0766.1
TASA b2.5Base Model=Qwen2.5-7B, Bits=2.5, Calibration Data (Calib)=Mixed2026.0757.5
TASA b2.5Base Model=LLaMA-3-8B, Bits=2.5, Calibration Data (Calib)=Mixed2026.0754.7
GPTQBase Model=LLaMA-3-8B, Bits=3.0, Calibration Data (Calib)=Wiki2026.0753.2