Evals for Every Language - Language ta: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 73.75 |
| 2 | Claude Opus 4.7 | 72.46 |
| 3 | GPT-5 | 72.25 |
| 4 | Gemini 3.1 Pro (Preview) | 71.59 |
| 5 | GPT-5.1 | 71.41 |
| 6 | Claude Sonnet 4 | 70.61 |
| 7 | Gemini 3.1 Flash Lite | 70.58 |
| 8 | Grok 4.20 | 70.52 |
| 9 | GPT-5.2 | 70.24 |
| 10 | Claude Sonnet 4.5 | 69.97 |
| 11 | GPT-5.3 | 69.96 |
| 12 | GPT-5.5 | 69.92 |
| 13 | Qwen 3.6 Plus | 69.45 |
| 14 | Claude Sonnet 4.6 | 69.4 |
| 15 | Claude Opus 4.8 | 69.29 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-ta · How It Works · Data refreshed daily, snapshot 2026-09-05.