Evals for Every Language - Belarusian (be): leaderboard
Average score across evaluation tasks in Belarusian (be), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around February 2027. 66 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 75.83 | #37 |
| 2 | Gemini 3.1 Pro (Preview) | 75.66 | #58 |
| 3 | Claude Sonnet 4.6 | 73.23 | #90 |
| 4 | GPT-5.1 | 72.45 | #135 |
| 5 | Mistral Medium 3.1 | 72.22 | #408 |
| 6 | Claude Opus 4.7 | 72 | #49 |
| 7 | GPT-4.1 | 71.75 | #248 |
| 8 | Claude Sonnet 4 | 71.71 | #199 |
| 9 | DeepSeek V3.1 | 71.57 | #264 |
| 10 | GPT-5 | 71.25 | #98 |
| 11 | Claude Sonnet 4.5 | 70.97 | #142 |
| 12 | jamba-large-1.7 | 70.91 | #525 |
| 13 | Qwen 3.6 Plus | 70.79 | #120 |
| 14 | GPT-5.3 | 69.96 | #103 |
| 15 | GPT-5.5 | 69.91 | #31 |
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-be · How It Works · Data refreshed daily, snapshot 2026-10-20.