GPT-5.6 Terra
OpenAI · 6 thinking configurations
Intelligence42.1
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 max · 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.
42.1 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.
69.6 % ±2.6GPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
92.5 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
42.9 %SciCodeCode generation for scientific research problems.
55.0 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
88.0 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
86.3 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
71.2 %MMMU-ProMultimodal understanding of academic problems that include images.
80.7 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
46.8 %Specifications from the catalog
Inputfile, image, text
Outputtext
Tool callingYes
Structured outputYes
Speed92.7 tok/s
First token171.90 s
Maximum output128K
Catalog listing date2026-07-09
DeepSWE v1.1 · 113 tasks · mini-swe-agent · cost $4.95 / task · 76 mean steps · 71.9K mean output tokens. Published by the source 9/22/2026.