GaelEval - Linguistic Competence (Gaelic Prompt): leaderboard
Metric: Accuracy (%) on the 120-item Gaelic morphosyntactic MCQA with a Gaelic-language system prompt, exact string match, single call per item, zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 83.3 |
| 2 | Gemini 3 Flash (Preview) | 79.2 |
| 3 | GPT-5 | 69.2 |
| 4 | Gemini 2.5 Flash | 61.7 |
| 5 | Claude Opus 4.6 | 59.2 |
| 6 | GPT-4o | 50 |
| 7 | GPT-5 Mini | 47.5 |
| 8 | Claude Haiku 4.5 | 47.5 |
| 9 | DeepSeek R1 | 45 |
| 10 | Llama 4 Maverick | 45 |
| 11 | GPT-5.2 | 43.3 |
| 12 | GPT-4.1 | 42.5 |
| 13 | GPT-5 Nano | 36.7 |
| 14 | GPT-4o Mini | 34.2 |
| 15 | GPT-OSS-120B | 33.3 |
Interactive version: theaggregate.ai/benchmark?slug=gaeleval-linguistic-competence-gaelic-prompt · How It Works · Data refreshed daily, snapshot 2026-10-07.