GaelEval - English to Gaelic Translation (chrF): leaderboard
Metric: chrF character n-gram F-score of English-to-Gaelic translation against gold references; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 79.07 |
| 2 | Gemini 3 Pro (Preview) | 78.57 |
| 3 | Gemini 2.5 Flash | 74.72 |
| 4 | GPT-4.1 | 74.62 |
| 5 | GPT-5.2 | 72.16 |
| 6 | DeepSeek R1 | 71.84 |
| 7 | GPT-5 | 70.27 |
| 8 | Claude Opus 4.6 | 69.34 |
| 9 | GPT-4o | 67.83 |
| 10 | Llama 4 Maverick | 62.3 |
| 11 | GPT-5 Mini | 60.93 |
| 12 | Claude Haiku 4.5 | 59.27 |
| 13 | GPT-4.1 Mini | 58.01 |
| 14 | GPT-4o Mini | 56.84 |
| 15 | GPT-5 Nano | 55.54 |
Interactive version: theaggregate.ai/benchmark?slug=gaeleval-english-to-gaelic-translation-chrf · How It Works · Data refreshed daily, snapshot 2026-10-07.