SAHARA - General Knowledge: leaderboard
General-knowledge multiple-choice questions (mmlu) in African languages, from the SAHARA African-language LLM leaderboard (UBC-NLP, ACL 2025). The task score is the mean over the languages the task covers; Accuracy on a 0-100 scale, higher is better.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 48 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 94.8 | #71 |
| 2 | Gemini 2.5 Pro | 94.61 | #159 |
| 3 | GPT-5 | 92.81 | #105 |
| 4 | GPT-5.1 (2025-11-13) | 91.5 | #107 |
| 5 | GPT-5.6 Luna | 90.8 | #79 |
| 6 | Gemini 2.5 Flash | 89.4 | #255 |
| 7 | Claude Sonnet 4 (20250514) | 81.6 | #223 |
| 8 | Qwen 3.5 27B | 71.6 | #192 |
| 9 | Qwen 3.6 27B | 68.29 | #182 |
| 10 | Qwen 3.6 35B A3B | 62.8 | #238 |
| 11 | c4ai-command-a-03-2025 | 61.91 | #468 |
| 12 | Claude Sonnet 4 | 61.21 | #207 |
| 13 | Gemma 3 27B (IT) | 60.71 | #528 |
| 14 | Llama 3.3 70B Instruct | 59.3 | #541 |
| 15 | GPT-4.1 | 58.6 | #258 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=sahara-general-knowledge · How It Works · Data refreshed daily, snapshot 2026-11-05.