AfroBench-Lite: leaderboard
Cost-efficient AfroBench subset for African-language model evaluation, covering representative task and dataset scores with expanded recent model coverage. (Source: benchmarklist.com, self-reported.)
Metric: Average score (imported). Source: benchmarklist.com. 24 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 (Aug) | 77.74 | |
| 2 | Gemini 3 Pro | 76.01 | #80 |
| 3 | Gemini-2.5 Pro | 74.53 | |
| 4 | Claude 4.5 Sonnet | 70.6 | |
| 5 | Claude 4.0 Sonnet | 68.69 | |
| 6 | Gemini-2.5 Flash | 66.71 | |
| 7 | Gemini-2.0 Flash | 66.43 | |
| 8 | GPT-4o (Aug) | 65.8 | |
| 9 | GPT-4.1 (April) | 65.67 | |
| 10 | Gemini 1.5 pro | 62.79 |
Interactive version: theaggregate.ai/benchmark?slug=afrobench-lite · How It Works · Data refreshed daily, snapshot 2026-10-20.