GPT-4o mini
OpenAI · 1 configuration
Intelligence6.7
Input / 1M$0.15
Output / 1M$0.60
Context128K
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 · 0 without both values
Selected: thinking default · Click a point to switch configuration
GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
6.7 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
42.6 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
4.2 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
5.6 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
31.0 %MMMU-ProMultimodal understanding of academic problems that include images.
41.5 %Specifications from the catalog
Inputtext, image, file
Outputtext
Tool callingYes
Structured outputYes
Speed119.3 tok/s
First token0.84 s
Maximum output16.4K
Catalog listing date2024-07-18