Evals for Every Language - Language mr — leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 74.38 |
| 2 | Grok 4.20 | 73.46 |
| 3 | Claude Opus 4.7 | 72.98 |
| 4 | Claude Sonnet 4.6 | 72.54 |
| 5 | GPT-5.1 | 72.4 |
| 6 | GPT-5.5 | 72.25 |
| 7 | Gemini 3.1 Flash Lite | 72.09 |
| 8 | GPT-5.2 | 71.59 |
| 9 | Claude Opus 4.8 | 70.84 |
| 10 | Claude Sonnet 4 | 70.36 |
| 11 | Qwen 3.6 Plus | 69.53 |
| 12 | GPT-5 | 69.33 |
| 13 | Claude Sonnet 4.5 | 68.94 |
| 14 | Gemini 2.5 Pro | 68.8 |
| 15 | GPT-5.4 | 67.83 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-mr · How the rankings work · Data refreshed daily, snapshot 2026-07-22.