OpenAI

GPT Terra 5.6 High

Version 5.6 benchmark runs across the shared Superbash visual prompts.

Official benchmark profile

How GPT Terra 5.6 High scores beyond our visual tests.

OpenAI positions Terra as the capable lower-cost GPT-5.6 option. These rows use the shared GPT-5.6 comparison table so the scores line up against Sol, Luna, GPT-5.5, Claude, and Gemini where published.

OpenAI sourceJuly 2026Source report →

Coding

SWE-bench Pro

63.4%

Agentic coding

Terminal-Bench 2.1

87.4%

Computer use

OSWorld 2.0

50.2%

Full official benchmark table9 rows with source settings and peer charts

Benchmark	Area	Score	Setting / comparison
SWE-bench Pro	Coding	63.4%	Shared OpenAI GPT-5.6 comparison table. Claude Fable 580.0% Claude Opus 4.869.2% GPT-5.6 Sol64.6% GPT Terra 5.6 High63.4% GPT-5.6 Luna62.7% GPT-5.559.4% Gemini 3.1 Pro54.2%
Terminal-Bench 2.1	Agentic coding	87.4%	Shared OpenAI GPT-5.6 comparison table. GPT-5.6 Sol88.8% GPT Terra 5.6 High87.4% GPT-5.585.6% GPT-5.6 Luna84.7% Claude Fable 583.1% Claude Opus 4.878.9% Gemini 3.1 Pro70.7%
OSWorld 2.0	Computer use	50.2%	High-effort computer-use comparison table. GPT-5.6 Sol62.6% Claude Opus 4.854.8% GPT Terra 5.6 High50.2% GPT-5.547.5% GPT-5.6 Luna45.6%
BrowseComp	Tool use	87.5%	High-effort browsing-agent comparison table. GPT-5.6 Sol Ultra92.2% GPT-5.6 Sol90.4% Claude Mythos 588.0% Claude Mythos Preview87.9% GPT Terra 5.6 High87.5% Gemini 3.1 Pro85.9% GPT-5.584.4% Claude Opus 4.884.3%
BenchCAD	Computer-aided design	62.3%	Vision2Code score without Python tool. GPT-5.6 Sol70.6% GPT-5.6 Luna63.1% GPT Terra 5.6 High62.3% GPT-5.544.4% Claude Mythos 538.4% Claude Mythos Preview35.5% Claude Opus 4.827.3%
BenchCAD with Python tool	Tool use	78.2%	Vision2Code score with Python tool. GPT-5.6 Sol83.4% GPT Terra 5.6 High78.2% GPT-5.6 Luna73.9% GPT-5.559.4% Claude Mythos 556.7% Claude Mythos Preview56.4% Claude Opus 4.848.1%
GPQA Diamond	Academic reasoning	92.9%	Shared reasoning benchmark table. GPT-5.6 Sol94.6% Gemini 3.1 Pro94.3% Claude Mythos 594.1% GPT-5.593.6% GPT Terra 5.6 High92.9% Claude Fable 592.6% GPT-5.6 Luna92.3% Claude Opus 4.892.0%
FrontierMath Tier 1-3 v2	Math	84.9%	Shared reasoning benchmark table. GPT-5.6 Sol89.0% Claude Fable 587.0% GPT-5.585.3% GPT Terra 5.6 High84.9% Claude Opus 4.880.0% GPT-5.6 Luna78.6% Gemini 3.1 Pro59.6%
FrontierMath Tier 4 v2	Math	68.3%	Shared reasoning benchmark table. Claude Fable 587.8% GPT-5.6 Sol83.0% GPT-5.572.5% GPT Terra 5.6 High68.3% GPT-5.6 Luna58.5% Claude Opus 4.856.1%

Visual prompt runs

Benchmark runs

Open each generated scene, or compare the same prompt across models.

9 runs

Helm's Deep

Fortress siege scene testing scale, lighting, architecture, and cinematic atmosphere.

Open run →Compare models →

Hogwarts Broom Flight Simulator

Broom-flight scene testing depth, motion cues, castle scale, and fantasy mood.

Open run →Compare models →

Jabberwock

Dark fantasy encounter testing creature design, forest mood, and narrative staging.

Open run →Compare models →

Low Poly World

Stylized island build testing composition, color, and low-poly worldbuilding.

Open run →Compare models →

Office Life

Workplace vignette testing everyday scene logic, objects, and believable office detail.

Open run →Compare models →

Petri Dish

Microscopic ecosystem testing organic forms, scientific clarity, and cellular detail.

Open run →Compare models →

Universe Simulator

Cosmic system testing orbital structure, glowing bodies, scale, and simulation readability.

Open run →Compare models →

Vice City

Neon coastal city testing vehicles, architecture, atmosphere, and dense urban layout.

Open run →Compare models →

Yingzao Fashi Assembly

Timber assembly scene testing structure, joinery, construction order, and material clarity.

Open run →Compare models →