Commonsense Reasoning on HellaSwag (HS)
85.87AccuracyQwen3-235B-A22B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-235B-A22B#Bits=W16A16, Regime=PTQ, Zero-shot=true, Architecture=MoE2026.06 | 85.87 | |
| Llama2-70B#Bits=W16A16, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 83.86 | |
| Qwen3-32B#Bits=W16A16, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 82.66 | |
| RF2-100B-A6.1B#Bits=W16A16, Regime=PTQ, Zero-shot=true, Architecture=MoE2026.06 | 79.27 | |
| Qwen3-14B#Bits=W16A16, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 78.83 | |
| Qwen3-30B-A3B#Bits=W16A16, Regime=PTQ, Zero-shot=true, Architecture=MoE2026.06 | 77.66 | |
| Llama2-7B#Bits=W16A16, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 75.9 | |
| Qwen3-8B#Bits=W16A16, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 74.92 | |
| CAT-QBase Model=Llama2-70B, #Bits=W1.58A16, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 74.56 | |
| CAT-QBase Model=Qwen3-32B, #Bits=W1.58A16, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 74.33 | |
| CAT-QBase Model=Qwen3-235B-A22B, #Bits=W1.58A16, Regime=PTQ, Zero-shot=true, Architecture=MoE2026.06 | 74.02 | |
| Qwen3-4B#Bits=W16A16, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 68.41 | |
| CAT-QBase Model=RF2-100B-A6.1B, #Bits=W1.58A16, Regime=PTQ, Zero-shot=true, Architecture=MoE2026.06 | 67.46 | |
| CAT-QBase Model=Qwen3-14B, #Bits=W1.58A16, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 67.19 | |
| CAT-QBase Model=Qwen3-30B-A3B, #Bits=W1.58A16, Regime=PTQ, Zero-shot=true, Architecture=MoE2026.06 | 63.22 | |
| CAT-QBase Model=Llama2-7B, #Bits=W1.58A16, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 60.95 | |
| Qwen3-1.7B#Bits=W16A16, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 60.36 | |
| CAT-QBase Model=Qwen3-8B, #Bits=W1.58A16, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 59.57 | |
| CAT-QBase Model=Qwen3-8B, #Bits=W1.58A8, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 58.64 | |
| CAT-QBase Model=Qwen3-4B, #Bits=W1.58A16, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 53.24 | |
| CAT-QBase Model=Qwen3-4B, #Bits=W1.58A8, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 51.48 | |
| CAT-QBase Model=Qwen3-1.7B, #Bits=W1.58A16, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 47.77 | |
| CAT-QBase Model=Qwen3-1.7B, #Bits=W1.58A8, Regime=PTQ, Zero-shot=true, Architecture=Dense2026.06 | 47.22 |