SAGE
Math · 2025-10-08
Student Assessment with Generative Evaluation benchmark for evaluating or grading student responses with generative models.
Top models (higher is better)
| Model | Score |
|---|---|
| Opus 4.7 | 56.1 |
| Gemma 4 31B IT | 55.0 |
| Opus 4.8 | 54.8 |
| Gemini 4 Argon | 53.6 |
| Kimi K3 | 52.8 |
| GPT-5.6 Sol | 52.6 |
| Qwen3.8 27B | 52.4 |
| Opus 4.5 | 52.1 |
| Claude Fable 5 | 51.9 |
| Gemini 3 Flash Preview | 51.8 |
| Claude Sonnet 5.5 | 51.8 |
| Opus 4.6 | 51.6 |
| GPT-5.5 | 51.5 |
| Qwen3.8-Max | 51.3 |
| GPT-5.4 Mini | 50.8 |
| MiniMax M3 | 50.6 |
| Kimi K2.6 | 50.2 |
| Gemini 3.5 Flash | 49.9 |
| Kimi K2.5 | 49.9 |
| Gemini 3.1 Flash-Lite Preview | 49.5 |
| Claude Opus 5 | 49.4 |
| GPT-5.2 | 49.3 |
| Gemini 3.7 Flash | 49.2 |
| Sonnet 5 | 48.9 |
| Gemini 3.6 Flash | 48.7 |
| Gemini 3.1 Pro Preview | 48.7 |
| Claude Fable 5.1 | 48.5 |
| GPT-6 Luna | 48.1 |
| DeepSeek V4.1 Flash | 47.9 |
| Muse Spark 1.2 | 47.7 |
| Gemini 3 Pro Preview | 47.6 |
| Gemini 3.5 Flash-Lite | 47.3 |
| GPT-5.6 Terra | 47.0 |
| Sonnet 4.6 | 46.6 |
| GPT-6.1 Sol | 46.5 |
| GPT-6 Astra | 46.4 |
| Claude Opus 5.5 | 45.8 |
| Claude Haiku 5.5 | 45.8 |
| Muse Spark 1.1 | 45.6 |
| Qwen3.6 27B | 45.6 |