Observed arrival · 2026-10-11
Naija LLM Benchmarks
An open leaderboard compares language models on Nigerian-language tasks, alongside a hub of datasets and models.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Researchers and builders evaluating AI for Nigerian languages
- Worth noticing
- The overall score averages task categories on Nigerian and African-language benchmarks, excluding English-only tests.
Field notes
The methodology section names the metrics used for individual benchmarks and explains that task scores are plain averages. Model conditions vary: open models are run locally with MLX at 8-bit precision, while named hosted models use provider APIs and settings. The page also flags sample-size exceptions for some evaluations, so its comparisons include visible caveats rather than presenting every result as directly equivalent.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue