Evals for Every Language - Silesian (szl): leaderboard
Average score across evaluation tasks in Silesian (szl), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 66 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 76.74 | #31 |
| 2 | Gemini 3.1 Pro (Preview) | 76.06 | #58 |
| 3 | Claude Opus 4.8 | 75.71 | #37 |
| 4 | Claude Sonnet 4.5 | 75.59 | #142 |
| 5 | Gemini 3.1 Flash Lite | 75.53 | #191 |
| 6 | GPT-5.1 | 75.11 | #135 |
| 7 | DeepSeek V3.2 Exp | 74.75 | #234 |
| 8 | GPT-5.2 | 74.7 | #110 |
| 9 | Claude Sonnet 4 | 74.56 | #199 |
| 10 | Gemini 2.5 Pro | 73.89 | #152 |
| 11 | Claude Opus 4.7 | 73.64 | #49 |
| 12 | Claude Sonnet 4.6 | 72.9 | #90 |
| 13 | GPT-5 | 72.85 | #98 |
| 14 | GPT-5.3 | 72.54 | #103 |
| 15 | Qwen 3.6 Plus | 72.24 | #120 |
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-szl · How It Works · Data refreshed daily, snapshot 2026-10-20.