Evals for Every Language - Greek (el): leaderboard
Average score across evaluation tasks in Greek (el), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 68 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Flash Lite | 79.42 | #191 |
| 2 | Gemma 3 27B (IT) | 78.38 | #523 |
| 3 | Gemini 3.1 Pro (Preview) | 78.3 | #58 |
| 4 | Nova Pro (v1) | 78.2 | #497 |
| 5 | GPT-5.1 | 77.8 | #135 |
| 6 | Claude Sonnet 4 | 77.72 | #199 |
| 7 | GPT-5.5 | 77.71 | #31 |
| 8 | DeepSeek V3.1 | 77.25 | #264 |
| 9 | Claude Sonnet 4.5 | 76.8 | #142 |
| 10 | DeepSeek V3.2 Exp | 76.25 | #234 |
| 11 | GPT-4o | 76.25 | #343 |
| 12 | GPT-5 | 76.24 | #98 |
| 13 | Claude Opus 4.7 | 76.07 | #49 |
| 14 | Claude Sonnet 4.6 | 75.65 | #90 |
| 15 | Llama 3.3 70B Instruct | 75.55 | #534 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-el · How It Works · Data refreshed daily, snapshot 2026-10-20.