SAGE - Calculus
Math · 2025-10-08
The Calculus split of SAGE. This child benchmark separates a source-reported subtask or subtrack from the parent aggregate so scores at different grains do not share one benchmark_slug.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 3.1 Pro Preview | 78.4 |
| Claude Opus 5 | 77.2 |
| Opus 4.7 | 75.9 |
| Kimi K3 | 75.6 |
| Gemini 3.6 Flash | 75.3 |
| Muse Spark 1.1 | 74.7 |
| Opus 4.5 | 73.5 |
| Opus 4.6 | 72.5 |
| GPT-5.5 | 72.2 |
| Gemini 3 Flash Preview | 71.0 |
| GPT-5.4 | 71.0 |
| Gemini 2.5 Pro | 70.7 |
| GPT-5.1 | 69.8 |
| Gemini 3 Pro Preview | 69.4 |
| GPT-5.6 Sol | 67.3 |
| GPT-5.6 Luna | 64.5 |
| GPT-5 | 63.0 |
| GPT-5.2 | 62.0 |
| Sonnet 4.5 | 60.8 |
| Sonnet 4.6 | 60.5 |
| Gemini 3.5 Flash-Lite | 60.5 |
| Grok 4.5 | 59.6 |
| Gemma 4 31B IT | 59.3 |
| GPT-5.4 Mini | 59.3 |
| GPT-5.6 Terra | 59.3 |
| Gemini 3.1 Flash-Lite Preview | 58.3 |
| Gemini 2.5 Flash | 55.9 |
| Gemini 2.5 Flash Preview (09-2025) | 55.6 |
| o3 | 55.6 |
| Haiku 4.5 | 49.4 |
| Grok 4.3 | 48.1 |
| Sonnet 4 | 46.6 |
| Qwen3.6 Plus (2026-04-02) | 46.6 |
| Opus 4.1 | 46.3 |
| Qwen3.5-Flash | 44.4 |
| Grok 4.20 | 40.1 |
| GPT-5 Mini | 39.8 |
| Gemini 2.5 Flash-Lite Preview (09-2025) | 36.4 |
| Grok 4.1 Fast | 33.3 |
| O4 Mini | 33.3 |