Evals for Every Language - Bambara (bm): leaderboard
Average score across evaluation tasks in Bambara (bm), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around April 2027. 65 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 67.51 | #58 |
| 2 | Claude Opus 4.8 | 67.27 | #37 |
| 3 | Claude Opus 4.7 | 65.04 | #49 |
| 4 | GPT-5.5 | 60.55 | #31 |
| 5 | Qwen 3.6 Plus | 56.05 | #120 |
| 6 | Gemini 2.5 Pro | 55.87 | #152 |
| 7 | Gemini 3.1 Flash Lite | 53.62 | #191 |
| 8 | Claude Sonnet 4.6 | 52.68 | #90 |
| 9 | GPT-5.4 | 51.58 | #79 |
| 10 | Grok 4.20 | 50.19 | #175 |
| 11 | GPT-5.3 | 46.81 | #103 |
| 12 | GPT-5.2 | 44.72 | #110 |
| 13 | Claude Sonnet 4.5 | 42.29 | #142 |
| 14 | GPT-5.1 | 41.45 | #135 |
| 15 | Gemini 2.5 Flash Lite | 40.46 | #422 |
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-bm · How It Works · Data refreshed daily, snapshot 2026-10-20.