Evals for Every Language - Luxembourgish (lb): leaderboard
Average score across evaluation tasks in Luxembourgish (lb), 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 | Claude Sonnet 4.5 | 77 | #142 |
| 2 | Gemini 3.1 Pro (Preview) | 76.22 | #58 |
| 3 | Claude Opus 4.8 | 75.68 | #37 |
| 4 | GPT-5 | 75.64 | #98 |
| 5 | Gemini 2.5 Pro | 75.62 | #152 |
| 6 | Claude Sonnet 4 | 75.5 | #199 |
| 7 | Grok 4.20 | 75.45 | #175 |
| 8 | GPT-5.3 | 75.15 | #103 |
| 9 | GPT-5.1 | 74.19 | #135 |
| 10 | Gemini 3.1 Flash Lite | 74.09 | #191 |
| 11 | GPT-5.2 | 73.9 | #110 |
| 12 | Claude Opus 4.7 | 73.15 | #49 |
| 13 | Claude Sonnet 4.6 | 72.99 | #90 |
| 14 | Nova Pro (v1) | 72.43 | #497 |
| 15 | GPT-5.5 | 72.36 | #31 |
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-lb · How It Works · Data refreshed daily, snapshot 2026-10-20.