Greek MMLU - Social Sciences — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 62 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 94.16 |
| 2 | GPT-5.2 | 90.29 |
| 3 | GPT-4o (2024-11-20) | 89.36 |
| 4 | Llama 3.3 70B Instruct | 82.92 |
| 5 | Llama 3.1 70B Instruct | 82.57 |
| 6 | Gemma 3 27B (IT) | 82.19 |
| 7 | Qwen 2.5 72B Instruct | 81.92 |
| 8 | Qwen 2.5 72B | 81.35 |
| 9 | gemma-3-27B-pt | 80.52 |
| 10 | Qwen 3 30B A3B 2507 Instruct | 79.33 |
| 11 | Gemma 3 12B (IT) | 79.28 |
| 12 | Llama 3.1 70B | 78.9 |
| 13 | gemma-3-12B-pt | 78.28 |
| 14 | Qwen 2.5 32B Instruct | 76.61 |
| 15 | Qwen 2.5 32B | 75.26 |
Interactive version: aibenchmarks.dev/benchmark?slug=greek-mmlu-social-sciences · How the rankings work · Data refreshed daily, snapshot 2026-07-08.