IndoBias: leaderboard
Despite being home to more than 1300 ethnic groups and 700 indigenous languages, bias in Large Language Models has not been fully studied in Indonesia, thus leaving a critical gap in evaluating representational fairness and localized stereotypes within its uniquely vast, multilingual, and diverse sociocultural landscape. To address this, we introduce IndoBias as a culturally-grounded bias benchmar
Metric: Ideology and Religion IND (self-reported). Source: benchmarklist.com. 26 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Sailor2-8B | 77.6 | |
| 2 | Merak-7B-v4 | 73.5 | |
| 3 | SahabatAI-Instruct | 71.4 | |
| 4 | Gemma-3-4B-PT | 71.4 | |
| 5 | Llama-3.1-8B | 71.4 | |
| 6 | Komodo-7B | 69.4 | |
| 7 | Sailor2-8B-Chat | 69.4 | #782 |
| 8 | SEA-LION-v3-IT | 69.4 | |
| 9 | Gemma-3-4B-IT | 69.4 | |
| 10 | Cendol-Llama2-7B-Chat | 67.3 |
Interactive version: theaggregate.ai/benchmark?slug=indobias · How It Works · Data refreshed daily, snapshot 2026-10-20.