all the models — AI benchmark observatory
← Models

GPT-5 mini

OpenAI · proprietary · gpt-5-mini-2025-08-07

A faster, more cost-efficient version of GPT-5 for well-defined tasks. Great for well-defined tasks and precise prompts with high reasoning capabilities at reduced cost.

AIME 2025GPQAHumanity's L

Benchmark scores

BenchmarkScore
AIME 20250.91
GPQA0.82
Humanity's Last Exam0.17

Pricing

  • OpenAI$0.25 / $2.00

Input / output per 1M tokens

AA metrics

No Artificial Analysis link yet.

Arena Elo

  • No Arena snapshot linked.