Evals for Every Language - Irish (ga): leaderboard
Average score across evaluation tasks in Irish (ga), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 67 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 80.01 | #142 |
| 2 | Gemini 3.1 Pro (Preview) | 79.52 | #58 |
| 3 | Grok 4.20 | 79.42 | #175 |
| 4 | Claude Sonnet 4 | 79.29 | #199 |
| 5 | Claude Opus 4.8 | 79.29 | #37 |
| 6 | Gemini 3.1 Flash Lite | 79.23 | #191 |
| 7 | Claude Sonnet 4.6 | 78.87 | #90 |
| 8 | Claude Opus 4.7 | 78.67 | #49 |
| 9 | GPT-5.1 | 78.53 | #135 |
| 10 | GPT-5.2 | 78.08 | #110 |
| 11 | GPT-4o | 78.02 | #343 |
| 12 | GPT-5 | 77.11 | #98 |
| 13 | Kimi K2 | 76.12 | #243 |
| 14 | GPT-5.5 | 75.85 | #31 |
| 15 | Qwen 3.6 Plus | 75.58 | #120 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-ga · How It Works · Data refreshed daily, snapshot 2026-10-20.