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

🇳🇱

Nederlands

1 benchmark runs · Dutch

#	Model	Score	Runs
1	Claude Fable 5Anthropic	100.0	1
2	Qwen3-Coder-30B-A3B-InstructOVH AI Endpoints (GRA)	100.0	1
3	Gemini 3.1 Flash LiteGoogle Gemini	100.0	1
4	Qwen2.5-VL-72B-InstructOVH AI Endpoints (GRA)	100.0	1
5	Mistral-Nemo-Instruct-2407OVH AI Endpoints (GRA)	100.0	1

🇩🇪

Deutsch

2 benchmark runs · German

#	Model	Score	Runs
1	Gemini 3.1 Pro Preview Custom ToolsGoogle Gemini	100.0	2
2	gpt-5-chat-latestOpenAI	100.0	3
3	Gemini 3.1 Pro PreviewGoogle Gemini	100.0	3
4	gpt-5-2025-08-07OpenAI	100.0	1
5	gpt-5.1-chat-latestOpenAI	100.0	1

🇫🇷

Français

1 benchmark runs · French

#	Model	Score	Runs
1	o3OpenAI	100.0	1
2	o1-2024-12-17OpenAI	100.0	1
3	Gemini Flash-Lite LatestGoogle Gemini	100.0	4
4	gpt-5.2OpenAI	100.0	1
5	o4-mini-2025-04-16OpenAI	100.0	1

🇪🇸

Español

3 benchmark runs · Spanish

#	Model	Score	Runs
1	gpt-4o-miniOpenAI	100.0	3
2	gpt-5.5OpenAI	100.0	1
3	gpt-5.5-2026-04-23OpenAI	100.0	1
4	Gemini 3.1 Flash LiteGoogle Gemini	100.0	3
5	Qwen2.5-VL-72B-InstructOVH AI Endpoints (GRA)	100.0	3

🇹🇷

Türkçe

1 benchmark runs · Turkish

#	Model	Score	Runs
1	Qwen2.5-VL-72B-InstructOVH AI Endpoints (GRA)	100.0	1
2	Gemini Robotics-ER 1.6 PreviewGoogle Gemini	100.0	1
3	gpt-4o-2024-11-20OpenAI	100.0	1
4	gpt-4.1OpenAI	100.0	1
5	gpt-oss-120bOVH AI Endpoints (GRA)	100.0	1