GaelEval - English to Gaelic Translation (BLEU): leaderboard

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

Top models

#ModelScore
1Gemini 3 Flash (Preview)71.47
2Gemini 3 Pro (Preview)65.56
3Gemini 2.5 Flash65.53
4GPT-4.165.41
5DeepSeek R162.12
6GPT-5.261.19
7GPT-556.94
8Claude Opus 4.653.16
9GPT-4o52.39
10GPT-5 Mini49.19
11Llama 4 Maverick42.93
12GPT-5 Nano42.56
13GPT-4.1 Mini38.9
14Claude Haiku 4.538.44
15GPT-OSS-120B37.79

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