Evals for Every Language - Turkmen (tk): leaderboard
Average score across evaluation tasks in Turkmen (tk), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 65 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 | 75.78 | #49 |
| 2 | Gemini 3.1 Pro (Preview) | 75 | #58 |
| 3 | Claude Opus 4.8 | 74.61 | #37 |
| 4 | Claude Sonnet 4.6 | 73.86 | #90 |
| 5 | Claude Sonnet 4.5 | 73.4 | #142 |
| 6 | GPT-5.3 | 72.72 | #103 |
| 7 | Grok 4.20 | 70.04 | #175 |
| 8 | GPT-5.5 | 69.74 | #31 |
| 9 | GPT-5.2 | 69.33 | #110 |
| 10 | GPT-5 | 69.26 | #98 |
| 11 | Claude Sonnet 4 | 69.09 | #199 |
| 12 | GPT-4o | 68.24 | #343 |
| 13 | Gemini 2.5 Pro | 67.52 | #152 |
| 14 | GPT-5.1 | 67.12 | #135 |
| 15 | Qwen 3.6 Plus | 66.96 | #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-tk · How It Works · Data refreshed daily, snapshot 2026-10-20.