Evals for Every Language - Thai (th): leaderboard
Average score across evaluation tasks in Thai (th), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 68 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 80.68 | #58 |
| 2 | Gemini 2.5 Pro | 80.36 | #152 |
| 3 | Claude Sonnet 4.5 | 79.43 | #142 |
| 4 | Claude Opus 4.8 | 79.35 | #37 |
| 5 | Gemini 3.1 Flash Lite | 79.18 | #191 |
| 6 | Claude Opus 4.7 | 79.1 | #49 |
| 7 | GPT-5.5 | 78.96 | #31 |
| 8 | Claude Sonnet 4.6 | 78.78 | #90 |
| 9 | GPT-4o | 78.64 | #343 |
| 10 | Grok 4.20 | 78.23 | #175 |
| 11 | Claude Sonnet 4 | 77.96 | #199 |
| 12 | GPT-5.1 | 77.94 | #135 |
| 13 | GPT-5.2 | 77.84 | #110 |
| 14 | GPT-4.1 | 77.7 | #248 |
| 15 | GPT-5.3 | 76.79 | #103 |
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-th · How It Works · Data refreshed daily, snapshot 2026-10-20.