# MY-FairnessBench

[Canonical page](https://www.mohtasham.dev/work/archive/my-fairness-bench)

A command-line benchmark for testing model bias in a Malaysian cultural, linguistic, and legal context.

2026. Research prototype. Role: Independent research build.

Most fairness benchmarks flatten away the details that matter in Malaysia. MY-FairnessBench keeps ethnicity, socio-economic history, Manglish, and code-switching in the test instead.

The CLI sends the same prompt through a set of international models and ILMU, Malaysia's first multimodal LLM. It then saves the responses to a timestamped Markdown report for comparison.

This is still a research prototype. The useful part is the framing: local bias cannot be measured well with examples written for a different social and legal setting.

## Facts

- Model integrations listed: 5. 

- Local evaluation context: MY. 

- Timestamped reports: .md. 

## How it works

1. Write a case: Frame a prompt around Malaysian context.

2. Run models: Send the same case through each configured provider.

3. Collect: Keep the raw responses together.

4. Compare: Look for differences in language and treatment.

5. Save: Write a dated Markdown report.

## Languages

- TypeScript: 26805 bytes

Private GitHub repository