MMLU (CoT): leaderboard
14,042 four-option multiple-choice questions across 57 subjects from elementary maths to law, collected from practice exams by a UC Berkeley-led team (ICLR 2021); chain-of-thought answers, accuracy.
Metric: Score (%). Source: arxiv.org. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.1 405B Instruct | 88.6 | #457 |
| 2 | Llama 3.1 70B Instruct | 86 | #561 |
| 3 | Llama 3 70B Instruct | 80.9 | #634 |
| 4 | Llama 3.1 8B Instruct | 73 | #1035 |
| 5 | Llama 3 8B Instruct | 65.3 | #1129 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mmlu-cot · How It Works · Data refreshed daily, snapshot 2026-10-20.