Evals for Every Language - Bashkir (ba): leaderboard
Average score across evaluation tasks in Bashkir (ba), 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 | Gemini 3.1 Pro (Preview) | 76.82 | #58 |
| 2 | GPT-5 | 73.93 | #98 |
| 3 | Claude Opus 4.8 | 73.13 | #37 |
| 4 | GPT-5.2 | 72.98 | #110 |
| 5 | GPT-5.1 | 72.88 | #135 |
| 6 | Claude Opus 4.7 | 72.47 | #49 |
| 7 | Gemini 3.1 Flash Lite | 72.13 | #191 |
| 8 | Grok 4.20 | 71.95 | #175 |
| 9 | Claude Sonnet 4.6 | 70.99 | #90 |
| 10 | Claude Sonnet 4.5 | 70.91 | #142 |
| 11 | DeepSeek V3.1 | 69.87 | #264 |
| 12 | Gemini 2.5 Pro | 69.29 | #152 |
| 13 | Claude Sonnet 4 | 68.96 | #199 |
| 14 | Qwen 3.6 Plus | 68.64 | #120 |
| 15 | Gemma 3 27B (IT) | 68.14 | #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-ba · How It Works · Data refreshed daily, snapshot 2026-10-20.