Evals for Every Language - Turkish (tr): leaderboard
Average score across evaluation tasks in Turkish (tr), 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) | 80.58 | #58 |
| 2 | GPT-4o | 78.33 | #343 |
| 3 | Claude Sonnet 4 | 78.02 | #199 |
| 4 | Gemini 3.1 Flash Lite | 77.95 | #191 |
| 5 | Claude Sonnet 4.5 | 77.31 | #142 |
| 6 | Grok 4.20 | 77.24 | #175 |
| 7 | GPT-5 | 77.24 | #98 |
| 8 | GPT-5.1 | 77.13 | #135 |
| 9 | Gemini 2.5 Pro | 76.91 | #152 |
| 10 | Claude Opus 4.8 | 76.88 | #37 |
| 11 | GPT-5.2 | 76.24 | #110 |
| 12 | GPT-4.1 | 76.08 | #248 |
| 13 | DeepSeek V3.2 Exp | 74.65 | #234 |
| 14 | GPT-5.5 | 74.51 | #31 |
| 15 | Claude Sonnet 4.6 | 74.41 | #90 |
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-tr · How It Works · Data refreshed daily, snapshot 2026-10-20.