GPT-5 mini
OpenAI · 3 thinking configurations
Intelligence16.8
Input / 1M$0.25
Output / 1M$2.00
Context400K
Tariff: OpenAI · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost1 measured configurations · 2 without both values
Selected: thinking high · Click a point to switch configuration
GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
16.8 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
82.8 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
21.5 %SciCodeCode generation for scientific research problems.
39.0 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
3.7 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
68.4 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
75.4 %MMMU-ProMultimodal understanding of academic problems that include images.
70.1 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
25.0 %Specifications from the catalog
Inputtext, image, file
Outputtext
Tool callingYes
Structured outputYes
Speed113.0 tok/s
First token56.67 s
Maximum output128K
Catalog listing date2025-08-07