Knowledge QA on GPQA (Accuracy, TPS, Speedup)
59.6AccuracyGLM-4.7-FP8
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| GLM-4.7-FP8Mode=Standalone2026.05 | 59.6 | — | 70.3 | — | |
| PARSETarget Model=GLM-4.7-FP8, Draft Model=Qwen3.5-9B2026.05 | 58.1 | — | 66.8 | 0.95 | |
| Qwen3.5-9BMode=Standalone2026.05 | 43.4 | — | — | — |