GPT-4o (Aug)
OpenAI · 1 configuration
Intelligence7.7
Input / 1M$2.50
Output / 1M$10.00
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 model for general reasoning, writing, coding, and tool-assisted tasks
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
7.7 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
52.1 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
2.3 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
28.9 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
36.0 %MMMU-ProMultimodal understanding of academic problems that include images.
56.3 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
23.7 %Specifications from the catalog
Inputtext, image
Outputtext
Tool callingYes
Structured outputNot available
Speed102.4 tok/s
First token1.11 s
Maximum output8.2K
Catalog listing date2024-11-21