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	gpt-oss-120bOVH AI Endpoints (GRA)	100.0	2
2	Qwen3-Coder-30B-A3B-InstructOVH AI Endpoints (GRA)	100.0	1
3	Mistral-Small-3.2-24B-Instruct-2506OVH AI Endpoints (GRA)	100.0	1
4	Gemini 3.1 Flash LiteGoogle Gemini	100.0	1
5	Claude Opus 4.8Anthropic	100.0	1

🇳🇱

Nederlands

3 benchmark runs · Dutch

#	Model	Score	Runs
1	Claude Opus 4.5Anthropic	98.3	3
2	Claude Opus 4.6Anthropic	98.0	3
3	Gemma 4 26B A4B ITGoogle Gemini	96.0	3
4	Gemma 4 31B ITGoogle Gemini	95.0	3
5	Gemini Flash-Lite LatestGoogle Gemini	94.3	3

🇩🇪

Deutsch

2 benchmark runs · German

#	Model	Score	Runs
1	Claude Sonnet 4Anthropic	100.0	2
2	gpt-5-search-api-2025-10-14OpenAI	100.0	2
3	Gemini 3.1 Flash LiteGoogle Gemini	100.0	1
4	Claude Sonnet 4.6Anthropic	100.0	2
5	Claude Opus 4.6Anthropic	100.0	2

🇫🇷

Français

1 benchmark runs · French

#	Model	Score	Runs
1	Gemini Flash-Lite LatestGoogle Gemini	100.0	1
2	Claude Opus 4Anthropic	100.0	1
3	Claude Opus 4.6Anthropic	100.0	1
4	gpt-4.1-miniOpenAI	99.0	1
5	Claude Sonnet 4Anthropic	99.0	1

🇪🇸

Español

1 benchmark runs · Spanish

#	Model	Score	Runs
1	gpt-oss-20bOVH AI Endpoints (GRA)	100.0	1
2	Nano BananaGoogle Gemini	100.0	2
3	gpt-3.5-turbo-0125OpenAI	100.0	2
4	Qwen3-32BOVH AI Endpoints (GRA)	100.0	1
5	gpt-4o-2024-08-06OpenAI	100.0	1

🇹🇷

Türkçe

1 benchmark runs · Turkish

#	Model	Score	Runs
1	gpt-4o-2024-05-13OpenAI	100.0	1
2	gpt-5-chat-latestOpenAI	100.0	1
3	gpt-5-search-api-2025-10-14OpenAI	100.0	1
4	gpt-4.1-nanoOpenAI	100.0	1
5	gpt-4.1-nano-2025-04-14OpenAI	100.0	1