Evals for Every Language - Iloko (ilo): leaderboard
Average score across evaluation tasks in Iloko (ilo), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 65 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 77.64 | #58 |
| 2 | Gemini 3.1 Flash Lite | 76.49 | #191 |
| 3 | Claude Opus 4.7 | 75.94 | #49 |
| 4 | Grok 4.20 | 74.68 | #175 |
| 5 | Claude Sonnet 4.6 | 74.65 | #90 |
| 6 | DeepSeek V3.1 | 74.38 | #264 |
| 7 | Claude Sonnet 4 | 74.08 | #199 |
| 8 | Gemini 2.5 Pro | 73.41 | #152 |
| 9 | GPT-5 | 72.65 | #98 |
| 10 | GPT-5.5 | 72.39 | #31 |
| 11 | Qwen 3.6 Plus | 72 | #120 |
| 12 | Claude Sonnet 4.5 | 71.77 | #142 |
| 13 | Claude Opus 4.8 | 71.54 | #37 |
| 14 | GPT-5.4 | 69.77 | #79 |
| 15 | GPT-5.1 | 68.37 | #135 |
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-ilo · How It Works · Data refreshed daily, snapshot 2026-10-20.