Evals for Every Language - Bemba (bem): leaderboard
Average score across evaluation tasks in Bemba (bem), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around March 2027. 65 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 70.94 | #58 |
| 2 | Claude Opus 4.8 | 66.58 | #37 |
| 3 | Gemini 3.1 Flash Lite | 64.69 | #191 |
| 4 | Claude Opus 4.7 | 62.19 | #49 |
| 5 | DeepSeek V3.1 | 61.19 | #264 |
| 6 | GPT-5.4 | 59.12 | #79 |
| 7 | Claude Sonnet 4.6 | 56.97 | #90 |
| 8 | Gemini 2.5 Pro | 56.8 | #152 |
| 9 | GPT-5.5 | 55.93 | #31 |
| 10 | Grok 4.20 | 54.97 | #175 |
| 11 | Claude Sonnet 4.5 | 53.09 | #142 |
| 12 | GPT-4o | 51.09 | #343 |
| 13 | GPT-5.2 | 50.9 | #110 |
| 14 | GPT-5.3 | 49.78 | #103 |
| 15 | GPT-5.1 | 49.16 | #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-bem · How It Works · Data refreshed daily, snapshot 2026-10-20.