Evals for Every Language - Language sw: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 76.71 |
| 2 | Gemini 3.1 Flash Lite | 76.38 |
| 3 | Claude Sonnet 4.6 | 75.73 |
| 4 | Claude Opus 4.7 | 75.42 |
| 5 | Grok 4.20 | 75.01 |
| 6 | Claude Opus 4.8 | 74.3 |
| 7 | GPT-5.3 | 73.55 |
| 8 | GPT-5.2 | 73.32 |
| 9 | GPT-5.5 | 72.27 |
| 10 | GPT-5.4 | 71.91 |
| 11 | Qwen 3.6 Plus | 70.23 |
| 12 | Qwen 3.6 Flash | 68.76 |
| 13 | Gemini 2.5 Pro | 67.18 |
| 14 | GPT-5.1 | 66.86 |
| 15 | Claude Sonnet 4.5 | 66.17 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-sw · How It Works · Data refreshed daily, snapshot 2026-09-05.