Versions

1 version · Metric: Average accuracy

Versions of Multi-task Indic Language Understanding Benchmark
VersionReleasedModelsResults
MILU OriginalLatestNovember 4, 202477

Recently reported results: MILU Original

Latest version: MILU Original

Recently reported results for MILU Original
ModelScoreSource
Claude Haiku 5.5 (max)87.6%anthropic.com for Claude Haiku 5.5 (max) on Multi-task Indic Language Understanding Benchmark Original (opens in a new tab)Archived copy (opens in a new tab)Average accuracyReported System cardAnthropicSelf-reportedRecord for Claude Haiku 5.5 on Multi-task Indic Language Understanding Benchmark Original
Claude Sonnet 5.5 (max)91.6%anthropic.com for Claude Sonnet 5.5 (max) on Multi-task Indic Language Understanding Benchmark Original (opens in a new tab)Average accuracyReported System cardAnthropicSelf-reportedRecord for Claude Sonnet 5.5 on Multi-task Indic Language Understanding Benchmark Original
Claude Opus 5.5 (max)93.1%www-cdn.anthropic.com for Claude Opus 5.5 (max) on Multi-task Indic Language Understanding Benchmark Original (opens in a new tab)Average accuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5.5 on Multi-task Indic Language Understanding Benchmark Original
Claude Fable 5.1 (max)93.0%www-cdn.anthropic.com for Claude Fable 5.1 (max) on Multi-task Indic Language Understanding Benchmark Original (opens in a new tab)Average accuracyReported System cardAnthropicSelf-reportedRecord for Claude Fable 5.1 on Multi-task Indic Language Understanding Benchmark Original
Claude Opus 5 (max)92.1%www-cdn.anthropic.com for Claude Opus 5 (max) on Multi-task Indic Language Understanding Benchmark Original (opens in a new tab)Average accuracyReported System cardAnthropicSelf-reportedRecord for Claude Opus 5 on Multi-task Indic Language Understanding Benchmark Original