GaelEval - Cultural Knowledge (English Prompt): leaderboard
GaelEval (2026) is a Scottish Gaelic benchmark from the DR-LIB project. This board is accuracy in percent on 1,087 four-option questions about Gaelic culture that an LLM generated from transcripts of the An Litir Bheag learner podcast and filtered for answerability, asked with an English-language prompt; higher is better.
Metric: Accuracy (%) on the 1087-question Gaelic cultural-knowledge MCQ with an English-language prompt, four options; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 19 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 91.63 | #152 |
| 2 | Gemini 3 Pro (Preview) | 90.98 | #119 |
| 3 | GPT-5 | 88.5 | #178 |
| 4 | Claude Opus 4.6 | 83.53 | #113 |
| 5 | Gemini 2.5 Flash | 83.44 | #463 |
| 6 | GPT-5 Mini | 80.04 | #364 |
| 7 | DeepSeek R1 | 75.53 | #482 |
| 8 | GPT-4.1 | 74.7 | #505 |
| 9 | GPT-4o | 73.41 | #751 |
| 10 | GLM-4.7 | 72.4 | #380 |
| 11 | GPT-5.2 | 70.65 | #185 |
| 12 | GPT-OSS-120B | 70.56 | #704 |
| 13 | GPT-5 Nano | 70.29 | #906 |
| 14 | Llama 4 Maverick | 70.01 | #1110 |
| 15 | GPT-4.1 Mini | 65.59 | #789 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=gaeleval-cultural-knowledge-english-prompt · How It Works · Data refreshed daily, snapshot 2026-11-21.