live
weekly refresh
basedagi.org
▸ vertical

What is the best LLM
across languages?

Ranked from two independent public multilingual suites: Artificial Analysis Global-MMLU-Lite and the AI Language Proficiency Monitor. The general ranking uses one aggregate row per source. It does not let ten language columns count as ten separate votes. A named winner also requires 20 callable models with current two-source coverage.

no current multilingual performance winner published

No current winner is published: qualifying independent evidence is older than 30 days. The table below shows available corroborated evidence, not a publishable current winner.

corroborated evidence · multilingual score
#ModelMultilingualReasoningPrice/M
1Anthropic: Claude Opus 4.6
Anthropic
95.0-$5.00/M
2Anthropic: Claude Sonnet 4.6
Anthropic
93.767.9$3.00/M
3Anthropic: Claude Opus 4.5
Anthropic
93.471.4$5.00/M
4OpenAI: GPT-5.2
Openai
92.267.6$1.75/M
5Anthropic: Claude Sonnet 4.5
Anthropic
92.143.1$3.00/M
6Google: Gemini 2.5 Pro
Google
92.053.2$1.25/M
7Anthropic: Claude Haiku 4.5
Anthropic
88.7-$1.00/M
8Meta: Llama 4 Maverick
Meta Llama
86.452.2$0.15/M
9Meta: Llama 3.3 70B Instruct
Meta Llama
81.060.4$0.10/M
10Meta: Llama 4 Scout
Meta Llama
77.1-$0.10/M
11Google: Gemini 2.5 Flash
Google
58.629.2$0.30/M
▸ evidence used
Global-MMLU-Litecross-language knowledge · Artificial Analysis · independent
AI Language Proficiency MonitorARC + MGSM + MMLU · ten languages · independent
▸ scoring rule

The Language Proficiency Monitor row averages Arabic, Bengali, German, Spanish, French, Hindi, Japanese, Portuguese, Russian, and Mandarin Chinese.

Each included model must have the full ten-language, three-task panel. Missing tests do not quietly produce an inflated average.

Per-language scores are stored for the next niche pages. They are not duplicate weight in this broad ranking.

▸ rankings by language

Each page computes its own two-source composite. Russian is withheld until a second independent per-language source is available.

▸ frequently asked

What is the best multilingual LLM?

No current winner is published: qualifying independent evidence is older than 30 days.

How is the multilingual ranking calculated?

The composite uses one aggregate score from Artificial Analysis Global-MMLU-Lite and one from the independently published AI Language Proficiency Monitor. Per-language rows are kept for language-specific rankings, not multiplied into this broad score.