WMT25 English-Bhojpuri chrF++ — leaderboard
Metric: chrF++. Source: github.com. 35 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 40.6 |
| 2 | DeepSeek V3 | 36 |
| 3 | GPT-4.1 | 35.6 |
| 4 | Llama 4 Maverick | 34.4 |
| 5 | Gemma 3 27B | 32.4 |
| 6 | Mistral Medium | 31.6 |
| 7 | Qwen 3 235B A22B | 29.2 |
| 8 | aya-expanse-32B | 28.9 |
| 9 | Gemma 3 12B | 27.9 |
| 10 | aya-expanse-8B | 22.9 |
| 11 | Qwen 2.5 7B | 21.8 |
| 12 | Mistral 7B | 18.2 |
| 13 | Llama 3.1 8B | 2.3 |
Interactive version: theaggregate.ai/benchmark?slug=wmt25-english-bhojpuri-chrf-plus-plus · How the rankings work · Data refreshed daily, snapshot 2026-07-22.