AfroBench: How Good are Large Language Models on African Languages?

A product launch page for a benchmark: black-weight question headline, a pulsing yellow announcement, and three white stat cards on a cool off-white floor.

mcgill-nlp.github.io/AfroBenchAfroBench: How Good are Large Language Models on African Languages?
Screenshot of https://mcgill-nlp.github.io/AfroBench/, © the authors. Shown for reference. Request removal
Venue
ACL 2025 Findings
Year
2025
First author
Jessica Ojo
Field
multilingual LLM evaluation
Template
hand-written Tailwind CSS (CDN) page
Theme
Light

Checked against the rendered page. The selection note calls the nav sticky; the render shows a static (non-sticky) bar, recorded in the file.

Why it is here

Reads like a product site rather than a template. It has a sticky top nav, a bold question headline, three stat cards and a framed overview map, then a two-column text-plus-scatter section. The yellow announcement banner is a little loud.

Overview

Color Palette

Typography

system-ui sans
AfroBench: How Good are Large Language Models on African Languages? Abstract · Method · Results · BibTeX — 0123456789
ui-monospace
AfroBench: How Good are Large Language Models on African Languages? Abstract · Method · Results · BibTeX — 0123456789

Spacing & Shape

Page Modules

Guidelines

More like this