MATH-MC Level 2: leaderboard
MATH-MC Level 2 evaluates multiple-choice mathematical reasoning on low-intermediate MATH problems.
Metric: Accuracy (%). Source: github.com. Saturation forecast: Estimated already saturated. 69 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 99.66 | #63 |
| 2 | Gemma 4 26B A4B (IT) | 99.32 | #297 |
| 3 | Gemini 3.1 Pro (Preview) | 99.21 | #58 |
| 4 | GPT-5.5 | 99.21 | #31 |
| 5 | Qwen 3.5 27B | 99.09 | #187 |
| 6 | Kimi K2.5 | 98.98 | #144 |
| 7 | Qwen 3.5 397B A17B | 98.98 | #146 |
| 8 | Gemma 4 31B (IT) | 98.87 | #176 |
| 9 | Kimi K2.6 | 98.87 | #104 |
| 10 | Qwen 3.5 35B A3B | 98.87 | #256 |
| 11 | Qwen 3.6 Plus | 98.87 | #120 |
| 12 | Qwen 3.5 9B | 98.75 | #379 |
| 13 | Qwen 3.5 122B A10B | 98.75 | #173 |
| 14 | Kimi K2 (Thinking) | 98.75 | #243 (Kimi K2) |
| 15 | OLMo 3.1 32B (Thinking) | 98.75 | #632 (OLMo 3.1 32B) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=math-mc-level-2 · How It Works · Data refreshed daily, snapshot 2026-10-20.