SeaEval - Multilingual Reasoning - CMMLU (Zero-Shot): leaderboard
Metric: Accuracy (%). Source: huggingface.co. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 83.44 |
| 2 | Qwen 2 72B Instruct | 82.94 |
| 3 | Qwen 2.5 32B Instruct | 82.73 |
| 4 | Qwen 2.5 14B Instruct | 78.08 |
| 5 | Qwen 2 7B Instruct | 77.28 |
| 6 | SeaLLMs-v3-7B-Chat | 76.84 |
| 7 | Qwen 2.5 7B Instruct | 74.87 |
| 8 | Llama 3.1 70B Instruct | 68.15 |
| 9 | Qwen 2.5 3B Instruct | 66.21 |
| 10 | Llama 3 70B Instruct | 64.95 |
| 11 | Sailor2-8B-Chat | 64.17 |
| 12 | Qwen 2.5 1.5B Instruct | 59.76 |
| 13 | gemma2-9B-cpt-sea-lionv3-instruct | 57.96 |
| 14 | Gemma 2 9B (IT) | 57 |
| 15 | Llama 3.1 8B Instruct | 51.83 |
Interactive version: theaggregate.ai/benchmark?slug=seaeval-multilingual-reasoning-cmmlu-zero-shot · How It Works · Data refreshed daily, snapshot 2026-09-05.