General Reasoning Evaluation on Reasoning Benchmarks Aggregate
70.63Average ScoreBF16
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BF16Model=Qwen3-4B, W-Bits=BF162026.01 | 70.63 | — | |
| Reasoning-QATModel=Qwen3-4B, W-Bits=W3G1282026.01 | 62.38 | -8.25 | |
| GPTQModel=Qwen3-4B, W-Bits=W3G1282026.01 | 54.96 | -15.67 | |
| AWQModel=Qwen3-4B, W-Bits=W3G1282026.01 | 51.8 | -18.83 | |
| BF16Model=R1-Qwen-1.5B, W-Bits=BF162026.01 | 48.72 | — | |
| Reasoning-QATModel=R1-Qwen-1.5B, W-Bits=W3G1282026.01 | 43.26 | -5.46 | |
| Reasoning-QATModel=Qwen3-4B, W-Bits=W2G1282026.01 | 41.89 | -28.74 | |
| BF16Model=Qwen3-0.6B, W-Bits=BF162026.01 | 41.1 | — | |
| GPTQModel=R1-Qwen-1.5B, W-Bits=W3G1282026.01 | 38.07 | -10.65 | |
| AWQModel=R1-Qwen-1.5B, W-Bits=W3G1282026.01 | 32.13 | -16.58 | |
| Reasoning-QATModel=Qwen3-0.6B, W-Bits=W3G1282026.01 | 31.67 | -9.43 | |
| Reasoning-QATModel=R1-Qwen-1.5B, W-Bits=W2G1282026.01 | 28.18 | -20.54 | |
| Reasoning-QATModel=Qwen3-0.6B, W-Bits=W2G1282026.01 | 15.27 | -25.83 | |
| GPTQModel=Qwen3-0.6B, W-Bits=W3G1282026.01 | 12.61 | -28.49 | |
| RTNModel=R1-Qwen-1.5B, W-Bits=W3G1282026.01 | 10.08 | -38.64 | |
| AWQModel=Qwen3-0.6B, W-Bits=W3G1282026.01 | 8.4 | -32.7 | |
| GPTQModel=Qwen3-4B, W-Bits=W2G1282026.01 | 6.16 | -64.47 | |
| GPTQModel=R1-Qwen-1.5B, W-Bits=W2G1282026.01 | 5.68 | -43.04 | |
| AWQModel=Qwen3-4B, W-Bits=W2G1282026.01 | 5.12 | -65.61 | |
| RTNModel=Qwen3-0.6B, W-Bits=W3G1282026.01 | 5.07 | -36.03 | |
| AWQModel=R1-Qwen-1.5B, W-Bits=W2G1282026.01 | 5.02 | -43.7 | |
| AWQModel=Qwen3-0.6B, W-Bits=W2G1282026.01 | 4.78 | -36.32 | |
| RTNModel=Qwen3-4B, W-Bits=W3G1282026.01 | 2.6 | -68.03 | |
| GPTQModel=Qwen3-0.6B, W-Bits=W2G1282026.01 | 0.31 | -40.79 |