Evals for Every Language - Balinese (ban): leaderboard
Average score across evaluation tasks in Balinese (ban), 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) | 72.7 | #58 |
| 2 | Claude Opus 4.7 | 72.66 | #49 |
| 3 | DeepSeek V3.1 | 72.24 | #264 |
| 4 | GPT-5.1 | 69.95 | #135 |
| 5 | Claude Opus 4.8 | 69.76 | #37 |
| 6 | Qwen 3.6 Plus | 68.8 | #120 |
| 7 | GPT-5.5 | 68.79 | #31 |
| 8 | Grok 4.20 | 68.66 | #175 |
| 9 | Claude Sonnet 4.6 | 68.25 | #90 |
| 10 | GPT-5.4 | 68.08 | #79 |
| 11 | GPT-5.3 | 67.91 | #103 |
| 12 | Claude Sonnet 4 | 67.03 | #199 |
| 13 | Claude Sonnet 4.5 | 66.47 | #142 |
| 14 | GPT-5 | 66.47 | #98 |
| 15 | Qwen 3.6 Flash | 65.61 | #214 |
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-ban · How It Works · Data refreshed daily, snapshot 2026-10-20.