GPT-5.6 Terra
OpenAI · 6 thinking configurations
Intelligence30.1
Input / 1M$2.00
Output / 1M$12.00
Context1M
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 cost6 measured configurations · 0 without both values
Selected: thinking medium · Click a point to switch configuration
GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
30.1 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.
35.1 % ±3.4GPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
87.2 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
33.3 %SciCodeCode generation for scientific research problems.
50.5 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
72.3 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
72.8 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
62.2 %MMMU-ProMultimodal understanding of academic problems that include images.
76.8 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
44.6 %Specifications from the catalog
Inputfile, image, text
Outputtext
Tool callingYes
Structured outputYes
Speed76.7 tok/s
First token1.79 s
Maximum output128K
Catalog listing date2026-07-09
DeepSWE v1.1 · 113 tasks · mini-swe-agent · cost $0.58 / task · 25 mean steps · 11.7K mean output tokens. Published by the source 9/22/2026.