Evals for Every Language - Limburgish (li): leaderboard
Average score across evaluation tasks in Limburgish (li), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 66 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 77.88 | #58 |
| 2 | Claude Sonnet 4.5 | 77.47 | #142 |
| 3 | Gemini 3.1 Flash Lite | 76.97 | #191 |
| 4 | Claude Sonnet 4.6 | 76.7 | #90 |
| 5 | Gemini 2.5 Pro | 76.08 | #152 |
| 6 | Claude Opus 4.8 | 75.96 | #37 |
| 7 | GPT-5.2 | 75.78 | #110 |
| 8 | GPT-5 | 75.66 | #98 |
| 9 | GPT-5.3 | 75.5 | #103 |
| 10 | Claude Sonnet 4 | 74.55 | #199 |
| 11 | Qwen 3.6 Flash | 74.5 | #214 |
| 12 | Qwen 3.6 Plus | 74.23 | #120 |
| 13 | Nova Pro (v1) | 73.96 | #497 |
| 14 | GPT-5.4 | 73.88 | #79 |
| 15 | Gemma 3 27B (IT) | 73.66 | #523 |
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-li · How It Works · Data refreshed daily, snapshot 2026-10-20.