OpenAI

GPT Sol 5.6 High

Version 5.6-high benchmark runs across the shared Superbash visual prompts.

Official benchmark profile

How GPT Sol 5.6 High scores beyond our visual tests.

OpenAI presents Sol as the flagship GPT-5.6 model. These rows use the shared GPT-5.6 comparison table so the scores can be read directly against Terra, Luna, GPT-5.5, Claude, and Gemini where published.

OpenAI sourceJuly 2026Source report →

Coding

SWE-bench Pro

64.6%

Agentic coding

Terminal-Bench 2.1

88.8%

Computer use

OSWorld 2.0

62.6%

Full official benchmark table9 rows with source settings and peer charts

Benchmark	Area	Score	Setting / comparison
SWE-bench Pro	Coding	64.6%	Shared OpenAI GPT-5.6 comparison table. Claude Fable 580.0% Claude Opus 4.869.2% GPT Sol 5.6 High64.6% GPT-5.6 Terra63.4% GPT-5.6 Luna62.7% GPT-5.559.4% Gemini 3.1 Pro54.2%
Terminal-Bench 2.1	Agentic coding	88.8%	Shared OpenAI GPT-5.6 comparison table. GPT Sol 5.6 High88.8% GPT-5.6 Terra87.4% 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	62.6%	High-effort computer-use comparison table. GPT Sol 5.6 High62.6% Claude Opus 4.854.8% GPT-5.6 Terra50.2% GPT-5.547.5% GPT-5.6 Luna45.6%
BrowseComp	Tool use	90.4%	High-effort score; OpenAI separately reports Sol Ultra at 92.2%. GPT-5.6 Sol Ultra92.2% GPT Sol 5.6 High90.4% Claude Mythos 588.0% Claude Mythos Preview87.9% GPT-5.6 Terra87.5% Gemini 3.1 Pro85.9% GPT-5.584.4% Claude Opus 4.884.3%
BenchCAD	Computer-aided design	70.6%	Vision2Code score without Python tool. GPT Sol 5.6 High70.6% GPT-5.6 Luna63.1% GPT-5.6 Terra62.3% GPT-5.544.4% Claude Mythos 538.4% Claude Mythos Preview35.5% Claude Opus 4.827.3%
BenchCAD with Python tool	Tool use	83.4%	Vision2Code score with Python tool. GPT Sol 5.6 High83.4% GPT-5.6 Terra78.2% 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	94.6%	Shared reasoning benchmark table. GPT Sol 5.6 High94.6% Gemini 3.1 Pro94.3% Claude Mythos 594.1% GPT-5.593.6% GPT-5.6 Terra92.9% Claude Fable 592.6% GPT-5.6 Luna92.3% Claude Opus 4.892.0%
FrontierMath Tier 1-3 v2	Math	89.0%	Shared reasoning benchmark table. GPT Sol 5.6 High89.0% Claude Fable 587.0% GPT-5.585.3% GPT-5.6 Terra84.9% Claude Opus 4.880.0% GPT-5.6 Luna78.6% Gemini 3.1 Pro59.6%
FrontierMath Tier 4 v2	Math	83.0%	Shared reasoning benchmark table. Claude Fable 587.8% GPT Sol 5.6 High83.0% GPT-5.572.5% GPT-5.6 Terra68.3% 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 →