GPT-5.5
OpenAI · 5 thinking configurations
Intelligence33.8
Input / 1M$5.00
Output / 1M$30.00
Context922K
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 cost3 measured configurations · 2 without both values
Selected: thinking medium · Click a point to switch configuration
GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
33.8 pointsDeepSWE · pass@1Software-engineering tasks on mini-swe-agent v1.1. Pass@1 across evaluated runs, with measured cost per task. The 95% intervals may overlap.
54.0 % ±2.6GPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
92.6 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
42.4 %SciCodeCode generation for scientific research problems.
54.5 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
80.5 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
91.8 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
71.0 %MMMU-ProMultimodal understanding of academic problems that include images.
81.2 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
56.8 %Specifications from the catalog
Inputfile, image, text
Outputtext
Tool callingYes
Structured outputYes
Speed83.9 tok/s
First token6.81 s
Maximum output128K
Catalog listing date2026-04-24
DeepSWE v1.1 · 113 tasks · mini-swe-agent · cost $2.75 / task · 46 mean steps · 19.6K mean output tokens. Published by the source 9/22/2026.