GaelEval - Gaelic to English Translation (BLEU): leaderboard

Metric: BLEU-4 of Gaelic-to-English translation of An Litir Bheag transcripts against gold references; higher is better. Source: arxiv.org. Saturation forecast: Around May 2027. 19 models tracked.

Top models

#ModelScore
1DeepSeek R175.28
2Gemini 2.5 Flash74.36
3Llama 4 Maverick73.49
4Gemini 3 Pro (Preview)73.41
5Claude Haiku 4.572.32
6Gemini 3 Flash (Preview)71.75
7GPT-5.271.02
8Claude Opus 4.670.37
9GPT-570.27
10GPT-5 Mini69.58
11GPT-4.1 Mini69.09
12GPT-4o Mini69.01
13GPT-4o68.73
14GPT-4.166.6
15GPT-4.1 Nano63.31

Interactive version: theaggregate.ai/benchmark?slug=gaeleval-gaelic-to-english-translation-bleu · How It Works · Data refreshed daily, snapshot 2026-10-07.