GSM-MC: leaderboard
GSM-MC evaluates grade-school math reasoning in a multiple-choice format.
Metric: Accuracy (%). Source: github.com. Saturation forecast: Estimated already saturated. 68 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 99.47 | #58 |
| 2 | GPT-5.5 | 99.47 | #31 |
| 3 | Gemma 4 31B (IT) | 99.47 | #176 |
| 4 | Claude Opus 4.6 | 99.39 | #63 |
| 5 | Kimi K2.6 | 99.39 | #104 |
| 6 | Qwen 3.5 27B | 99.39 | #187 |
| 7 | MiniMax-M2.5 | 99.39 | #303 |
| 8 | Step 3.5 Flash | 99.32 | #270 |
| 9 | Kimi K2.5 | 99.24 | #144 |
| 10 | GPT-5 Mini | 99.24 | #186 |
| 11 | Qwen 3.5 397B A17B | 99.24 | #146 |
| 12 | Qwen 3.5 35B A3B | 99.24 | #256 |
| 13 | Qwen 3.5 122B A10B | 99.24 | #173 |
| 14 | GLM-5.1 FP8 | 99.24 | #109 |
| 15 | GPT-OSS-120B | 99.17 | #341 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=gsm-mc · How It Works · Data refreshed daily, snapshot 2026-10-20.