Evals for Every Language - Bangla (bn): leaderboard
Average score across evaluation tasks in Bangla (bn), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 67 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4 | 78.71 | #199 |
| 2 | Gemini 3.1 Pro (Preview) | 78.47 | #58 |
| 3 | GPT-5.3 | 78.02 | #103 |
| 4 | Claude Opus 4.7 | 77.95 | #49 |
| 5 | GPT-5.2 | 77.73 | #110 |
| 6 | Grok 4.20 | 77.2 | #175 |
| 7 | GPT-5 | 77.01 | #98 |
| 8 | Gemini 3.1 Flash Lite | 76.76 | #191 |
| 9 | Claude Sonnet 4.6 | 76.38 | #90 |
| 10 | GPT-5.1 | 75.46 | #135 |
| 11 | Claude Opus 4.8 | 75.2 | #37 |
| 12 | Claude Sonnet 4.5 | 75.14 | #142 |
| 13 | Gemini 2.5 Pro | 74.95 | #152 |
| 14 | GPT-5.5 | 74.49 | #31 |
| 15 | Qwen 3.6 Plus | 74.31 | #120 |
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-bn · How It Works · Data refreshed daily, snapshot 2026-10-20.