Evals for Every Language - Ukrainian (uk): leaderboard
Average score across evaluation tasks in Ukrainian (uk), 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) | 78.5 | #58 |
| 2 | GPT-4o | 77.89 | #343 |
| 3 | Claude Sonnet 4.6 | 77.89 | #90 |
| 4 | Claude Sonnet 4.5 | 77.74 | #142 |
| 5 | Gemini 2.5 Pro | 77.48 | #152 |
| 6 | Claude Sonnet 4 | 77.37 | #199 |
| 7 | GPT-5.1 | 77.21 | #135 |
| 8 | GPT-5 | 77.21 | #98 |
| 9 | Gemini 3.1 Flash Lite | 77.02 | #191 |
| 10 | Mistral Medium 3.1 | 76.82 | #408 |
| 11 | Claude Haiku 4.5 | 76.77 | #280 |
| 12 | Nova Pro (v1) | 76.52 | #497 |
| 13 | Grok 4.20 | 76.1 | #175 |
| 14 | GPT-5.2 | 75.86 | #110 |
| 15 | Gemma 3 27B (IT) | 75.72 | #523 |
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-uk · How It Works · Data refreshed daily, snapshot 2026-10-20.