Mathematical Reasoning on GSM8K (Accuracy, Drop, TC2b)
96.13AccuracyQwen3-8B (FP16)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Qwen3-8B (FP16)Model=Qwen3-8B, Precision=FP162026.06 | 96.13 | — | — | |
| Qwen3-32B (FP16)Model=Qwen3-32B, Precision=FP162026.06 | 95.83 | — | — | |
| Qwen3-32B (+L)Model=Qwen3-32B, Precision=2-bit + loop rescue2026.06 | 93.48 | -2.5 | 99.77 | |
| Qwen3-32B (2bit)Model=Qwen3-32B, Precision=2-bit2026.06 | 93.33 | -2.5 | 99.77 | |
| Qwen3-32B (+P + L)Model=Qwen3-32B, Precision=2-bit + FP16 plan + loop rescue2026.06 | 92.65 | -2.5 | 99.77 | |
| Qwen3-32B (+P)Model=Qwen3-32B, Precision=2-bit + FP16 plan2026.06 | 92.49 | -2.5 | 99.77 | |
| Qwen3-8B (+P + L)Model=Qwen3-8B, Precision=2-bit + FP16 plan + loop rescue2026.06 | 80.06 | -43.44 | 27.14 | |
| Qwen3-8B (+L)Model=Qwen3-8B, Precision=2-bit + loop rescue2026.06 | 74.45 | -43.44 | 27.14 | |
| Qwen3-8B (+P)Model=Qwen3-8B, Precision=2-bit + FP16 plan2026.06 | 65.73 | -43.44 | 27.14 | |
| Qwen3-8B (2bit)Model=Qwen3-8B, Precision=2-bit2026.06 | 52.69 | -43.44 | 27.14 |