GPT-5.1
OpenAI · 2 thinking configurations
Intelligence24.7
Input / 1M$1.25
Output / 1M$10.00
Context272K
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 cost2 measured configurations · 0 without both values
Selected: thinking high · Click a point to switch configuration
GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
24.7 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
87.3 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
28.5 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
52.4 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
81.9 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
72.9 %MMMU-ProMultimodal understanding of academic problems that include images.
75.5 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
37.7 %Specifications from the catalog
Inputimage, text, file
Outputtext
Tool callingYes
Structured outputYes
Speed108.7 tok/s
First token38.40 s
Maximum output128K
Catalog listing date2025-11-13