Evals for Every Language - Language sv: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 77.13 |
| 2 | Gemini 3.1 Flash Lite | 76.58 |
| 3 | Claude Opus 4.8 | 75.68 |
| 4 | Claude Opus 4.7 | 74.85 |
| 5 | Claude Sonnet 4.6 | 74.31 |
| 6 | GPT-5.3 | 73.89 |
| 7 | Mistral Medium 3.1 | 73.73 |
| 8 | GPT-5.1 | 73.67 |
| 9 | Claude Sonnet 4 | 73.37 |
| 10 | GPT-5.2 | 73.12 |
| 11 | Llama 3.1 70B Instruct | 72.88 |
| 12 | Gemini 2.5 Pro | 72.72 |
| 13 | GPT-5.5 | 72.71 |
| 14 | Claude Sonnet 4.5 | 72.28 |
| 15 | GPT-5 | 72.26 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-sv · How It Works · Data refreshed daily, snapshot 2026-09-05.