Goobo Labs
Research
OverviewPublicationsBenchmarks (SomBench)Open SourceRoadmap
DatasetsModels
Learn
ProgramsLearning PathsCurriculum
BlogCommunity
Sign inExplore research
Goobo Labs

An open research lab building the foundations of Somali AI.

Research

  • Overview
  • Publications
  • Benchmarks
  • Roadmap

Datasets

  • SomNLP Corpus
  • SomNLP STT
  • Wikipedia Corpus
  • Citation Guide

Programs

  • Data Science & ML Bootcamp
  • Python for Everyone
  • NLP (coming soon)
  • Curriculum

Resources

  • Docs
  • Models & Tools
  • Open Source
  • Blog
  • Soplang

Contact

  • info@goobolabs.so
  • Mogadishu, Somalia

Company

  • About
  • Careers
  • Impact
  • Press Kit
  • Verify Certificate
  • Contact

Community

  • GitHub
  • Hugging Face
  • X
  • LinkedIn

© 2026 Goobo Labs. Open research for Somali AI.

Privacy PolicyTerms of Service
HomeBlogResearch
ResearchMar 4, 2026 · 8 min read

SomBench v0.1: a first benchmark for Somali NLP

We introduce SomBench — six tasks, clear splits, documented baselines, and an open leaderboard. Here's how we designed it, what we found, and how to submit your model.

Sharafdin Yusuf

Sharafdin Yusuf

Lead Engineer & Researcher

Today we're releasing SomBench v0.1: the first comprehensive benchmark for Somali NLP. It covers six tasks — classification, NER, translation, summarisation, QA, and ASR — with documented splits, evaluation code, and baselines from five multilingual models.

Why we need a benchmark

Without a shared evaluation standard, researchers can't compare results. A lab in Nairobi training a Somali NLP model has no reliable way to know whether their system is better or worse than one trained in Oslo. This slows progress and makes it hard to direct resources to where they'll have the most impact.

'Somali NLP performance' is not a measurable thing. Classification accuracy on news headlines, translation BLEU on spoken dialogue, and WER on radio speech are very different problems. SomBench treats them separately — each task has its own split, metric, and leaderboard column.

The six tasks

  • Text Classification — news category (6 classes), split from SomNLP-Corpus news domain
  • Named Entity Recognition — 3 entity types (PER, LOC, ORG), 8K annotated sentences
  • Translation — Somali↔English, 5K sentence pairs from held-out parallel corpus, BLEU metric
  • Summarisation — 1K Somali news articles with human-written summaries, ROUGE evaluation
  • Question Answering — 2.5K extractive QA pairs over Somali Wikipedia passages
  • ASR — 20-hour held-out split of SomNLP-STT-Corpus, WER metric

Baseline results

We ran five multilingual models: mBERT, XLM-RoBERTa-base, mDeBERTa-v3-base, afroXLMR-large, and our own goobo-base. The Somali-native model leads on overall score at 52.4, despite having far fewer parameters than afroXLMR-large.

Key finding: all multilingual models underperform significantly on morphology-sensitive Somali tasks. The gap is largest on NER, where the best general model achieves only 52.1 F1 — suggesting that standard contextual representations don't capture Somali's agglutinative structure well.

How to submit your model

SomBench uses an evaluation harness that runs your model on our held-out test sets (which we don't release publicly). Install the package, generate predictions, and email us your predictions file. We score and post results within 5 business days.

bash
# Install the evaluation harness
pip install sombench-eval

# Authenticate with your Hugging Face token
huggingface-cli login

# Run evaluation on classification task
sombench-eval \
  --task classification \
  --model your-org/your-model \
  --output predictions.jsonl

# Email predictions.jsonl to sombench@goobolabs.com

Open questions

SomBench v0.1 is deliberately narrow. Important tasks we haven't covered yet: sentiment analysis, hate speech detection, machine reading comprehension, and dialect identification. v1.0 (planned for late 2026) will expand the suite and release task papers for each.

ResearchBenchmarkNLPEvaluation
Sharafdin Yusuf

Sharafdin Yusuf

Lead Engineer & Researcher

Writing about Somali language technology, open data, and AI from the lab in Mogadishu.

All postsGet in touch

On this page

  • Why we need a benchmark
  • The six tasks
  • Baseline results
  • How to submit
  • Open questions

Share

Back to Blog
More from the lab

Related posts

Research6 min read

Introducing the Somali Language Standard (SLS) – Phase 1 Complete

We've formally published the first two standards of the Somali Language Standard (SLS) — an open, machine-readable, CI/CD-validated framework for the Somali language, starting with the alphabet and the standards process itself.

Jul 9, 2026Read
Research6 min read

Soplang v2.0.0: a compiler for the first Somali programming language

Our team shipped a Rust-based compiler for Soplang — Cranelift JIT and ahead-of-time builds, with syntax written entirely in Somali keywords.

Jun 30, 2026Read
Research7 min read

Why Somali needs its own tokenizer

Foreign multilingual tokenizers over-segment Somali — BERT-base spends 2.69 tokens per word. Our native BPE tokenizer, trained on 529M words of SomNLP-Corpus, gets that down to 1.53: a 1.75× improvement.

Nov 11, 2025Read
Newsletter

Stay in the loop

Dataset releases, new bootcamp cohorts, research papers, and lab updates — straight to your inbox. No spam, unsubscribe anytime.