NILEAGI-SUB · Available

Swahili Language Understanding

Sector-by-sector Swahili understanding under one controlled protocol. First report: education, SUB-MCQ EDUCATION with Level I results on compact open models.

2,569

Validated items

8

Open models (Level I)

27 pts

Accuracy spread (~2-5B)

Highlight · August 2026

SUB-MCQ EDUCATION

2,569 expert-reviewed Swahili multiple-choice items from the Swahili-subject curriculum (Standard 3-7 and Form 2-4). Featured in the Cohere Labs Open Science Community.

Items by grade

Grade bandItemsShare
Standard 3662.6%
Standard 41164.5%
Standard 527410.7%
Standard 665125.3%
Standard 751720.1%
Form 239915.5%
Form 31254.9%
Form 442116.4%
Total2,569100%

Level I results (~2-5B open models)

Eight open or openly accessible models evaluated on identical items with deterministic decoding and unified exact-match scoring. Accuracy spans about 27 points at a shared parameter budget. Chance baseline ≈ 22.4%.

#ModelParamsAccuracy
1Gemma 4 E4B4.5B54.8%
2AfriqueQwen3.5-4B4.0B50.3%
3AfriqueGemma-4B4.0B43.4%
4Tiny Aya Earth3.35B41.4%
5Tiny Aya Global3.35B40.7%
6Qwen3.5-4B4.0B35.4%
7Qwen3.5-2B2.0B29.1%
8Llama 3.2 3B3.2B27.8%

Resources

Full technical report

Methods, limitations, and grade-stratified results.