MMLU-by-task - College Mathematics: leaderboard
The "College Mathematics" subtask of MMLU-by-task. A single MMLU subject, reporting per-task multiple-choice accuracy from the MMLU-by-task leaderboard across a wide range of academic and professional domains.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 1257 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | StableBeluga2 | 44 | #1078 |
| 2 | OpenHermes-13B | 43 | #1393 |
| 3 | Llama 2 70B Chat | 41 | #1237 |
| 4 | Phi-1.5 | 41 | #1549 |
| 5 | Mistral-7B-v0.1 | 40 | #1326 |
| 6 | internlm-20B | 40 | #1296 |
| 7 | MPT-30B-Chat | 38 | #1451 |
| 8 | Llama 2 70B Base | 37 | #1025 |
| 9 | WizardLM-70B-V1.0 | 37 | #1236 |
| 10 | falcon-40B Instruct | 37 | #1458 |
| 11 | Xwin-LM-70B-V0.1 | 37 | #982 |
| 12 | Llama 2 7B Chat | 36 | #1499 |
| 13 | mpt-30B | 36 | #1476 |
| 14 | vicuna-7B-v1.3 | 36 | #1507 |
| 15 | RedPajama-INCITE-Base-3B-v1 | 36 | #1618 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mmlu-by-task-college-mathematics · How It Works · Data refreshed daily, snapshot 2026-10-20.