Evals for Every Language - Tamil (ta): leaderboard
Average score across evaluation tasks in Tamil (ta), 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 2.5 Pro | 78.53 | #152 |
| 2 | Claude Opus 4.7 | 77.37 | #49 |
| 3 | GPT-5 | 76.96 | #98 |
| 4 | GPT-5.1 | 76.37 | #135 |
| 5 | Grok 4.20 | 75.82 | #175 |
| 6 | GPT-5.3 | 75.34 | #103 |
| 7 | GPT-5.2 | 75.18 | #110 |
| 8 | Claude Sonnet 4 | 75.14 | #199 |
| 9 | Gemini 3.1 Pro (Preview) | 75.12 | #58 |
| 10 | Gemini 3.1 Flash Lite | 74.78 | #191 |
| 11 | Mistral Medium 3.1 | 74.37 | #408 |
| 12 | Claude Sonnet 4.5 | 74.14 | #142 |
| 13 | Nova Pro (v1) | 73.75 | #497 |
| 14 | GPT-5.5 | 73.69 | #31 |
| 15 | Claude Opus 4.8 | 73.65 | #37 |
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-ta · How It Works · Data refreshed daily, snapshot 2026-10-20.