SAGE v1.1 - Partial Differential Equations
Math · 2026-10-27
The Partial Differential Equations subject of SAGE v1.1, scored by class-balanced check accuracy over rubric deductions on handwritten PDE solutions.
Top models (higher is better)
| Model | Score |
|---|---|
| Qwen3.7-Plus (source unspecified) | 94.2 |
| Claude Opus 5.5 | 93.4 |
| GPT-5.6 Terra | 93.0 |
| Qwen3.5 397B A17B | 91.5 |
| Claude Sonnet 5.5 | 91.1 |
| Gemini 3.8 Flash | 91.1 |
| Gemma 4 31B IT | 90.7 |
| GPT-6.1 Sol | 90.7 |
| Gemini 3.1 Pro Preview | 90.5 |
| MiMo-V2.6-Pro | 90.5 |
| DeepSeek V4.1 Flash | 90.3 |
| MiniMax M3.1 Flash | 90.1 |
| Muse Spark Open | 89.9 |
| Claude Haiku 5.5 | 89.9 |
| Qwen3.5-Flash (source unspecified) | 89.6 |
| MiniMax M3 | 88.6 |
| Ember-1 | 88.0 |
| Grok 4.7 | 87.7 |
| Gemini 4 Argon | 87.0 |
| Kimi K3 | 86.3 |
| GLM-5.3 Flash | 86.1 |
| MiMo-V2.6-Flash | 86.0 |
| Gemini 3.5 Flash-Lite | 85.8 |
| GPT-6 Luna | 85.6 |
| Mistral Medium 3.5 | 81.2 |
| Grok 4.1 Fast | 77.5 |
| Mistral Small 4 | 68.4 |