WMT25 English-Maasai chrF++: leaderboard
WMT25 General Translation Task English-to-Maasai automatic chrF++ score for submitted machine translation systems.
Metric: chrF++. Source: github.com. Saturation forecast: Estimated already saturated. 27 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 235B A22B | 25.6 | #313 |
| 2 | Llama 4 Maverick | 25.4 | #464 |
| 3 | Gemini 2.5 Pro | 22.5 | #152 |
| 4 | DeepSeek V3 | 22.4 | #321 |
| 5 | aya-expanse-32B | 21.4 | #692 |
| 6 | Command A | 20.6 | #508 |
| 7 | Llama 3.1 8B | 20.4 | #1151 |
| 8 | EuroLLM-9B | 20.3 | #1254 |
| 9 | aya-expanse-8B | 20.2 | #931 |
| 10 | Qwen 2.5 7B | 19.9 | #922 |
| 11 | Gemma 3 12B | 19.6 | #671 |
| 12 | Mistral 7B | 17.1 | #1397 |
| 13 | Gemma 3 27B | 15.1 | #607 |
| 14 | GPT-4.1 | 13.4 | #248 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=wmt25-english-maasai-chrf-plus-plus · How It Works · Data refreshed daily, snapshot 2026-10-20.