Evals for Every Language - Language de: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 77.38 |
| 2 | Claude Sonnet 4.5 | 77.26 |
| 3 | Claude Opus 4.8 | 76.71 |
| 4 | Gemini 2.5 Pro | 76.67 |
| 5 | Claude Sonnet 4 | 75.83 |
| 6 | Claude Opus 4.7 | 75.66 |
| 7 | Claude Sonnet 4.6 | 75.44 |
| 8 | Gemini 3.1 Flash Lite | 75.35 |
| 9 | GPT-5.3 | 75.05 |
| 10 | Claude Haiku 4.5 | 74.81 |
| 11 | Grok 4.20 | 74.64 |
| 12 | GPT-5.2 | 74.52 |
| 13 | GPT-5.1 | 74.5 |
| 14 | GPT-5 | 74.17 |
| 15 | GPT-4o | 73.78 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-de · How It Works · Data refreshed daily, snapshot 2026-09-05.