Measuring AI Intelligence in African Contexts.

The Datalens Africa LLM Leaderboard is the definitive benchmark for evaluating AI understanding of African contexts. Compare how leading AI systems perform across language, culture, knowledge, and healthcare using the most comprehensive African evaluation framework.

Explore the Rankings View the Benchmarks

15k+

Questions

16+

Languages

32

Specialties

5

LLM Families

Rankings

African AI Benchmark Leaderboard

Rank

Model

AfriMCQA

AfriMMLU

MasakhaNEWS

AfriMedQA

Overall Score

👑1

GPT-5.1

OpenAI

81.22%

62.13%

78.61%

76.72%

74.67%

Gemini 2.5 Pro

Google

85.58%

79.47%

51.22%

75.95%

73.05%

DeepSeek-R1

DeepSeek AI

—

70.63%

73.87%

72.99%

72.50%

Claude Sonnet 4.6

Anthropic

79.33%

62.75%

68.75%

78.04%

72.22%

GPT-5.2

OpenAI

75.50%

67.38%

75.27%

69.97%

72.03%

Gemini 2.5 Flash

Google

81.05%

60.50%

71.20%

74.42%

71.79%

Grok 4.1 Fast Reasoning

xAI

72.60%

59.63%

64.90%

70.13%

66.81%

DeepSeek-V3.2

DeepSeek AI

—

61.50%

64.66%

71.06%

65.74%

Grok 4 Fast Reasoning

xAI

74.76%

54.13%

60.26%

71.32%

65.12%

Claude Haiku 4.5

Anthropic

63.46%

54.75%

67.72%

62.49%

62.10%

* Scores represent average performance across all benchmark sub-tasks in each dataset. Last updated: 22 Feb 2026.

AfriMCQA

Multilingual Cultural Understanding · Accuracy (%)

AfriMMLU

Knowledge & Reasoning Across Languages · Accuracy (%)

MasakhaNEWS

News Topic Classification · Macro-F1 (%)

AfriMedQA v2

Pan-African Clinical QA · Macro-Accuracy (%)

Benchmarks

Four Pillars of African AI Evaluation

Each benchmark targets a distinct dimension of African contextual understanding, spanning culture, language, and clinical medicine, and providing a multidimensional view of LLM capability.

Afri-MCQA

Multimodal, culturally-grounded multiple-choice questions in 16+ African languages, testing deep cultural and linguistic comprehension.

Culture Multilingual Multimodal

Languages 16+

Task Type MCQ / VQA

Metric Accuracy

AfriMMLU

Human-translated MMLU spanning 5 subjects across 17 African languages. Tests knowledge across geography, law, economics, global facts and mathematics.

Knowledge Reasoning Human-Translated

Subjects 5 Domains

Languages 17

Metric Accuracy

MasakhaNEWS

News topic classification across 16 African languages and 7 categories. Tests in-language understanding of real-world African news across diverse topics.

NLP Classification News

Categories 7 Topics

Languages 16

Metric Macro-F1

AfriMedQA v2

Pan-African medical QA dataset with 15,275 questions from 621 contributors across 16 countries, covering 32+ clinical specialties.

Medical Expert-Curated Healthcare

Questions 15,275

Specialties 32+

Metric Acc + ROUGE

Evaluated Models

Frontier AI Systems Under Review

OpenAI

GPT Series

GPT-5.1 and GPT-5.2 evaluated across all four African benchmarks in zero-shot and few-shot settings.

ModelsGPT-5.1 · GPT-5.2

Best Score74.67%

Google

Gemini Series

Gemini 2.5 Pro and Flash tested across all benchmark categories, with Pro leading on MMLU.

Models2.5 Pro · 2.5 Flash

Best Score73.05%

Anthropic

Claude Series

Claude Sonnet 4.6 and Haiku 4.5 evaluated; Claude Sonnet led all models on AfriMedQA.

ModelsSonnet 4.6 · Haiku 4.5

Best Score72.22%

DeepSeek AI

DeepSeek Series

DeepSeek-R1 and V3.2 evaluated; R1 excels on MMLU and MasakhaNEWS despite no AfriMCQA score.

ModelsR1 · V3.2

Best Score72.50%

xAI

Grok Series

Grok 4 Fast Reasoning and Grok 4.1 Fast Reasoning evaluated with web access disabled for fairness.

ModelsGrok 4 · Grok 4.1

Best Score66.81%

Community Note

Why This Leaderboard Matters

To our community,

We launched this leaderboard because a fundamental piece has been missing from the global AI conversation: a meaningful way to measure how well intelligent systems actually understand African realities.

For too long, Africa has remained at the margins of model evaluation—frequently included in rhetoric, but rarely represented in data, linguistic diversity, or contextual testing. This benchmark is our commitment to changing that narrative.

When AI systems fail to grasp African languages or misinterpret local contexts, the result isn’t just a technical glitch—it is digital exclusion. The future of intelligence cannot be built on a partial map of the world.

This leaderboard ensures that Africa is never an afterthought in global development. By building the data foundations and evaluation standards necessary for truly inclusive AI, we aren’t just measuring progress; we are shaping it.

Together, we can ensure Africa isn't just a spectator in the AI future, but a primary architect of it.

Best regards,

Olaoye Anthony Somide

Founder & CEO, CipherSense AI

Unlock the Full Potential of Your Data

Empower your organization with reliable, high-quality data pipelines that fuel smarter decisions, optimize operations, and unlock new opportunities.

Request Project Quote Join AI Talent Network