Benchmarks

Language performance

How well does each AI model perform when prompted in different languages? Scores are based on multilingual benchmark prompts written in native 6 languages.

Tests run weekly · Models with image/audio/TTS capabilities excluded

🇬🇧

English

2 benchmark runs · English

#	Model	Score	Runs
1	o1OpenAI	100.0	2
2	o4-mini-2025-04-16OpenAI	100.0	2
3	Claude Fable 5Anthropic	100.0	1
4	gpt-5.3-chat-latestOpenAI	100.0	2
5	gpt-5.4-nano-2026-03-17OpenAI	100.0	2

🇳🇱

Nederlands

1 benchmark runs · Dutch

#	Model	Score	Runs
1	Claude Opus 4.8Anthropic	100.0	1
2	Claude Fable 5Anthropic	100.0	1
3	Qwen3-32BOVH AI Endpoints (GRA)	100.0	1
4	gpt-oss-120bOVH AI Endpoints (GRA)	100.0	1
5	Qwen2.5-VL-72B-InstructOVH AI Endpoints (GRA)	100.0	1

🇩🇪

Deutsch

3 benchmark runs · German

#	Model	Score	Runs
1	gpt-4o-2024-05-13OpenAI	100.0	3
2	Claude Fable 5Anthropic	100.0	1
3	Claude Opus 4.8Anthropic	100.0	1
4	Gemini 3.1 Flash LiteGoogle Gemini	100.0	2
5	o1-2024-12-17OpenAI	100.0	1

🇫🇷

Français

1 benchmark runs · French

#	Model	Score	Runs
1	gpt-5.4-2026-03-05OpenAI	100.0	1
2	o4-miniOpenAI	100.0	1
3	Claude Opus 4Anthropic	100.0	2
4	gpt-5.2OpenAI	100.0	1
5	o1-2024-12-17OpenAI	100.0	1

🇪🇸

Español

3 benchmark runs · Spanish

#	Model	Score	Runs
1	Gemini 3.1 Flash LiteGoogle Gemini	100.0	3
2	gpt-4oOpenAI	100.0	3
3	gpt-4o-2024-05-13OpenAI	100.0	3
4	Claude Fable 5Anthropic	100.0	1
5	Gemini Robotics-ER 1.6 PreviewGoogle Gemini	100.0	3

🇹🇷

Türkçe

1 benchmark runs · Turkish

#	Model	Score	Runs
1	gpt-5.4-nano-2026-03-17OpenAI	100.0	1
2	gpt-5.4OpenAI	100.0	1
3	gpt-5.4-2026-03-05OpenAI	100.0	1
4	Gemini 3.5 FlashGoogle Gemini	100.0	1
5	Claude Sonnet 4Anthropic	100.0	1