Open PL LLM - Belebele (generative, 5-shot): leaderboard
Metric: Accuracy (%). Source: huggingface.co. 319 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral Large 2 (Nov) Instruct (2411) | 93.78 |
| 2 | DeepSeek V3 (0324) | 93.67 |
| 3 | QwQ 32B-Preview | 93.44 |
| 4 | Llama 3.1 405B Instruct FP8 | 93.22 |
| 5 | Mistral Large 2 (Jul) | 93 |
| 6 | Llama 3.3 70B Instruct | 92.78 |
| 7 | Qwen 2.5 32B | 92.56 |
| 8 | Qwen 2.5 32B Instruct | 92.44 |
| 9 | Llama 3.1 70B Instruct | 92 |
| 10 | QwQ-32B | 92 |
| 11 | Mistral Small 3 | 92 |
| 12 | Qwen 2.5 72B | 92 |
| 13 | Llama 3.1 Nemotron 70B Instruct | 92 |
| 14 | Qwen 2.5 72B Instruct | 91.89 |
| 15 | Qwen 3 32B | 91.89 |
Interactive version: theaggregate.ai/benchmark?slug=open-pl-llm-belebele-generative-5-shot · How It Works · Data refreshed daily, snapshot 2026-09-19.