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 |
| Kimi K3 | 54.3 |
| GPT-5.6 Sol | 52.6 |
| Opus 4.5 | 52.1 |
| Claude Fable 5 | 51.9 |
| Gemini 3 Flash Preview | 51.8 |
| Opus 4.6 | 51.6 |
| GPT-5.5 | 51.5 |
| 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 |
| Sonnet 5 | 48.9 |
| Gemini 3.6 Flash | 48.7 |
| Gemini 3.1 Pro Preview | 48.7 |
| Gemini 3 Pro Preview | 47.6 |
| Gemini 3.5 Flash-Lite | 47.3 |
| GPT-5.6 Terra | 47.0 |
| Sonnet 4.6 | 46.6 |
| Muse Spark 1.1 | 45.6 |
| Qwen3.6 27B | 45.6 |
| Qwen3.6 Plus (2026-04-02) | 44.9 |
| Gemini 2.5 Flash | 44.8 |
| GPT-5.6 Luna | 44.2 |
| Gemini 2.5 Flash Preview (09-2025) | 44.1 |
| GPT-5 | 43.7 |
| GPT-5.4 | 43.3 |
| MiMo-V2.5 | 43.3 |
| GPT-5.1 | 43.2 |
| GPT-5 Mini | 43.0 |
| Qwen3.5-Flash | 42.5 |
| Qwen3-VL-Plus-2025-09-23 | 42.1 |
| Gemini 2.5 Pro | 41.9 |
| o3 | 41.8 |