Benchmark Almanac

AfroBench

GPT-4o Aug 2024 59.6 leads since August 2024
Not in model cards

Models perform language understanding, reasoning, and generation tasks across 64 African languages. The full suite draws on 22 datasets.

The full suite covers 15 tasks. The authors also publish a reduced suite called AfroBench-Lite.

Made by
Jessica Ojo and colleagues
Released
November 2023
Kind
Knowledge in many languages
Level
School
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
Many languages
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Many languages
Strongest model tested
Gemini 1.5 Pro Sep 2024 #157 on the capability index
Last model added
September 2024
Scores refreshed
November 20th, 2026
12
Entries on its own leaderboard, 8 models we track

GPT-4o leads with 59.6 among models released by September 2024 GPT-4o leads with 59.6 among models released by September 2024

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

The newest model with a score here came out in September 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 GPT-4o Aug 2024 59.6
  2. 2 Gemini 1.5 Pro Sep 2024 58.5
  3. 3 Gemma 2 27B 47.9
  4. 4 Llama 3.1-70B 43.5
  5. 5 Gemma 2 9B 43.1
  6. 6 Aya-101 13B 40.3
  7. 7 LLaMAX3 8B 30.1
  8. 8 Llama 3.1-8B 29.5
  9. 9 Gemma1.1 7b 29.1
  10. 10 Llama 3-8B 28.8
  11. 11 Llama 2-7B 22.5
  12. 12 AfroLLaMa 8B 19.8

Source: Official AfroBench leaderboard

#EntryScoreSettingDateSource
1 GPT-4o Aug 2024 59.6 Aug 2024 Official leaderboard
2 Gemini 1.5 Pro Sep 2024 58.5 Sep 2024 Official leaderboard
3 Gemma 2 27B 47.9 Jun 2024 Official leaderboard
4 Llama 3.1-70B 43.5 Jul 2024 Official leaderboard
5 Gemma 2 9B 43.1 Jun 2024 Official leaderboard
6 Aya-101 13B 40.3 Official leaderboard
7 LLaMAX3 8B 30.1 Official leaderboard
8 Llama 3.1-8B 29.5 Jul 2024 Official leaderboard
9 Gemma1.1 7b 29.1 Official leaderboard
10 Llama 3-8B 28.8 Apr 2024 Official leaderboard
11 Llama 2-7B 22.5 Jul 2023 Official leaderboard
12 AfroLLaMa 8B 19.8 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-4o Aug 2024 59.6 Aug 2024 Official leaderboard
2 Gemini 1.5 Pro Sep 2024 58.5 Sep 2024 Official leaderboard
3 Gemma 2 27B 47.9 Jun 2024 Official leaderboard
4 Llama 3.1-70B 43.5 Jul 2024 Official leaderboard
5 Gemma 2 9B 43.1 Jun 2024 Official leaderboard
6 Llama 3.1-8B 29.5 Jul 2024 Official leaderboard
7 Llama 3-8B 28.8 Apr 2024 Official leaderboard
8 Llama 2-7B 22.5 Jul 2023 Official leaderboard

Rankings by part

We read 16 parts from the benchmark’s own leaderboard in 5 groups: qa, nlu, nlg, reasoning and knowledge. Each ranks models on one part of the test. Gemini 1.5 Pro leads 7 of them, and 3 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

XQA

8 models we track have a score here.

  1. 1 Gemma 2 27B ↑2 50.5
  2. 2 Gemma 2 9B ↑3 45.9
  3. 3 Llama 3.1-70B ↑1 44.0
  4. 4 GPT-4o Aug 2024 ↓3 43.4
  5. 5 Gemini 1.5 Pro Sep 2024 ↓3 40.5
  6. 6 Llama 3.1-8B 21.8
  7. 7 Llama 2-7B ↑1 13.7
  8. 8 Llama 3-8B ↓1 12.6

4 models have held number one on the official leaderboard since its release in November 2023

Lab claims count from the day the card came out, independent runs from the model’s release.

Meta Google DeepMind OpenAI
Own leaderboard Not tested since Sep 2024
GPT-4o 59.6

Source: Official AfroBench leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
20.0 30.0 40.0 50.0 60.0 2024 20.0 30.0 40.0 50.0 60.0 2024

Source: Official AfroBench leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Multilingual

All 545 in Multilingual
  • MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
  • WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET. K-EXAONE 90.5%
  • MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language. Qwen3.7-Max 87%
  • CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories. Solar Open 2 90.7%
  • Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
  • MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in September 2024, for Gemini 1.5 Pro. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (12 entries).
  • Pass Models scored 8 models we track, plus 4 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in September 2024, for Gemini 1.5 Pro.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 1.5 Pro (#157).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on mcgill-nlp.github.io: 8 rows for models we track and 4 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check