Evals for Every Language - Luo (luo): leaderboard
Average score across evaluation tasks in Luo (luo), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around February 2027. 61 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 | 70.19 | #49 |
| 2 | Claude Opus 4.8 | 69.85 | #37 |
| 3 | Gemini 3.1 Pro (Preview) | 69.34 | #58 |
| 4 | Gemini 3.1 Flash Lite | 66.45 | #191 |
| 5 | Gemini 2.5 Pro | 64.24 | #152 |
| 6 | Grok 4.20 | 62.88 | #175 |
| 7 | GPT-5.5 | 58.47 | #31 |
| 8 | Claude Sonnet 4.5 | 55.02 | #142 |
| 9 | Claude Sonnet 4.6 | 53.87 | #90 |
| 10 | GPT-5.4 | 53.72 | #79 |
| 11 | GPT-5.3 | 53.66 | #103 |
| 12 | GPT-5 | 52.55 | #98 |
| 13 | Claude Sonnet 4 | 50.77 | #199 |
| 14 | GPT-5.2 | 50.26 | #110 |
| 15 | GPT-4o | 49.16 | #343 |
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-luo · How It Works · Data refreshed daily, snapshot 2026-10-20.