Pedagogical Question Generation on K-12 Math
97.71UsabilityGLM-4-9B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GLM-4-9BPrompting Strategy=FGP2026.05 | 97.71 | 85.13 | |
| Spark3.5-MaxPrompting Strategy=FGP2026.05 | 97.48 | 82.15 | |
| InternLM3-8BPrompting Strategy=FGP2026.05 | 96.83 | 56.1 | |
| Qwen2.5-7BPrompting Strategy=FGP2026.05 | 96.79 | 81.88 | |
| Baichuan2-7BPrompting Strategy=FGP2026.05 | 95.66 | 81.51 | |
| Meta-LLaMA3-8BPrompting Strategy=FGP2026.05 | 94.51 | 83.52 |