modelgrep

Mistral: Mistral Large 3 2512 vs OpenAI: GPT-4.1 Mini

MMistral: Mistral Large 3 2512mistralai/mistral-large-2512VSOOpenAI: GPT-4.1 Miniopenai/gpt-4.1-mini

OpenAI: GPT-4.1 Mini wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricMistral: Mistral Large 3 2512OpenAI: GPT-4.1 Mini
Intelligence Index22.822.9✓
Coding Index22.7✓18.5
GPQA Diamond68%✓66%
Design Arena Elo1206✓1140
Speed (tokens/sec)3050✓
Latency787ms723ms✓
Input price /M$0.500$0.400✓
Output price /M$1.50✓$1.60
Context window262K1.0M✓
CapabilitiesToolsJSONVisionToolsJSONVision
Mistral: Mistral Large 3 2512 details →OpenAI: GPT-4.1 Mini details →