Evals for Every Language - Maithili (mai): leaderboard
Average score across evaluation tasks in Maithili (mai), 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 3.1 Pro (Preview) | 75.15 | #58 |
| 2 | Gemini 2.5 Pro | 74.39 | #152 |
| 3 | GPT-5.3 | 74.23 | #103 |
| 4 | GPT-5.1 | 73.68 | #135 |
| 5 | Claude Sonnet 4.5 | 73.35 | #142 |
| 6 | Claude Opus 4.7 | 73.19 | #49 |
| 7 | Claude Sonnet 4 | 72.94 | #199 |
| 8 | Claude Opus 4.8 | 72.61 | #37 |
| 9 | GPT-5 | 72.34 | #98 |
| 10 | GPT-5.5 | 71.85 | #31 |
| 11 | GPT-4.1 | 71.64 | #248 |
| 12 | Gemini 3.1 Flash Lite | 71.03 | #191 |
| 13 | GPT-5.2 | 70.78 | #110 |
| 14 | Qwen 3.6 Plus | 70.77 | #120 |
| 15 | Grok 4.20 | 70.5 | #175 |
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-mai · How It Works · Data refreshed daily, snapshot 2026-10-20.