Greek MMLU - Humanities — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 62 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 92.88 |
| 2 | GPT-4o (2024-11-20) | 88.68 |
| 3 | GPT-5.2 | 88.27 |
| 4 | Llama 3.1 70B Instruct | 82.34 |
| 5 | Llama 3.3 70B Instruct | 82.2 |
| 6 | Gemma 3 27B (IT) | 79.87 |
| 7 | gemma-3-27B-pt | 79.83 |
| 8 | Qwen 2.5 72B Instruct | 79.14 |
| 9 | Llama 3.1 70B | 79.05 |
| 10 | Qwen 2.5 72B | 78.78 |
| 11 | EuroLLM-22B-Instruct-2512 | 75.31 |
| 12 | Gemma 3 12B (IT) | 75.13 |
| 13 | Qwen 3 30B A3B 2507 Instruct | 74.81 |
| 14 | gemma-3-12B-pt | 74.44 |
| 15 | Mistral-Small-24B-Base-2501 | 74.07 |
Interactive version: aibenchmarks.dev/benchmark?slug=greek-mmlu-humanities · How the rankings work · Data refreshed daily, snapshot 2026-07-08.