Greek MMLU - Other: leaderboard
The Other subtask of Greek MMLU — miscellaneous-domain questions in Greek; accuracy (%).
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Around January 2027. 84 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 91.84 | #82 |
| 2 | GPT-5.2 | 85.96 | #110 |
| 3 | GPT-4o (2024-11-20) | 85.42 | #381 |
| 4 | Qwen 2.5 72B Instruct | 76.95 | #454 |
| 5 | gemma-3-27B-pt | 76.95 | #502 |
| 6 | Llama 3.3 70B Instruct | 76.8 | #534 |
| 7 | Qwen 2.5 72B | 76.75 | #499 |
| 8 | Qwen 3 30B A3B 2507 Instruct | 76.56 | #488 |
| 9 | Gemma 3 27B (IT) | 75.96 | #523 |
| 10 | Llama 3.1 70B Instruct | 75.61 | #561 |
| 11 | Llama 3.1 70B | 74.46 | #592 |
| 12 | Gemma 3 12B (IT) | 72.62 | #664 |
| 13 | gemma-3-12B-pt | 72.27 | #686 |
| 14 | Qwen 2.5 32B | 70.68 | #546 |
| 15 | EuroLLM-22B-Instruct-2512 | 70.08 | #701 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=greek-mmlu-other · How It Works · Data refreshed daily, snapshot 2026-10-20.