Evals for Every Language - German (de): leaderboard
Average score across evaluation tasks in German (de), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 67 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 80.72 | #58 |
| 2 | Claude Sonnet 4.5 | 80.69 | #142 |
| 3 | Gemini 2.5 Pro | 80.3 | #152 |
| 4 | Claude Opus 4.8 | 79.66 | #37 |
| 5 | Claude Sonnet 4 | 79.51 | #199 |
| 6 | Claude Sonnet 4.6 | 79.04 | #90 |
| 7 | Claude Haiku 4.5 | 78.92 | #280 |
| 8 | Claude Opus 4.7 | 78.79 | #49 |
| 9 | GPT-5.3 | 78.68 | #103 |
| 10 | Gemini 3.1 Flash Lite | 78.6 | #191 |
| 11 | Grok 4.20 | 78.4 | #175 |
| 12 | GPT-5.1 | 78.36 | #135 |
| 13 | GPT-5 | 78.09 | #98 |
| 14 | GPT-5.2 | 78.05 | #110 |
| 15 | Mistral Medium 3.1 | 77.76 | #408 |
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-de · How It Works · Data refreshed daily, snapshot 2026-10-20.