Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Multilingual benchmark
Multi-task Indic Language Understanding Benchmark. Every model the catalog carries a published MILU value for, ranked by that value.
Culturally grounded knowledge comprehension across ten Indic languages and English. 5 models in the ModelScale catalog have a published value.
Each point is a model with a published MILU value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
5 models with a published MILU value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Average accuracy |
|---|---|---|---|
| 1 | Anthropic | 94.1 | |
| 2 | Anthropic | 93.1 | |
| 3 | Anthropic | 93.0 |
What the benchmark measures and how its value is published, from the source’s own record.
MILU (Multi-task Indic Language Understanding Benchmark) is a multilingual benchmark published by MILU: A Multi-task Indic language understanding benchmark. Culturally grounded knowledge comprehension across ten Indic languages and English. Its evaluation set is described by the source as knowledge tasks across 11 languages. The source rates its difficulty as multilingual Indic knowledge.
Each model's result is published by MILU: A Multi-task Indic language understanding benchmark as average accuracy. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 5 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| 4 | Anthropic | 92.1 |
| 5 | Anthropic | 91.6 |
Evidence key: Observed
Rows are ordered by the value MILU: A Multi-task Indic language understanding benchmark published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.