P/RProofrunIndependent model tests / 008
Results brief 008 / Interface design / Published August 20, 2026

gpt-5.6-terra takes on Orbit Radio

A tactile sci-fi tuner that tests hierarchy, motion, and input handling.

Bounded resultopenai/gpt-5.6-terra produced a 78/100 artifact.Structured from the locked human evaluation. One run; no broader model rating is implied.
3 min readAugust 20, 2026Interface designproofrun-v0.7
Modelopenai/gpt-5.6-terra
Confidencemedium
Artifact score78/100
Requirements met6/6
01 / Publication evidence

The result,
shown before explained.

1
Model artifactopenai/gpt-5.6-terra
Publication evidenceModel artifact · Orbit Radio
Model artifact populated Orbit Radio capture
1280 × 720 original capture

Next was activated twice and Previous once from a fresh Orbit Radio load, then the resulting signal state was captured after the standardized stabilization window.

Model artifact · preserved capture
Score78
Wall time1:18
HTML start0:26
Cost$0.1206
“The model did a great job with the UI, one of the best visual designs I've seen for this result.”Locked before model reveal
02 / Frozen evaluation

Requirements first.
Weighted quality second.

Frozen requirements6 judgments per artifact
RequirementArtifact
The central dial responds to turning or dragging.Met
Five distinct fictional stations are available.Met
Station name, frequency, color, and visualization change together.Met
Previous and next controls work consistently.Met
The current station is visually unmistakable.Met
The single-file instrument remains responsive and works offline.Met
Weighted criteriaArtifact 78

Visual design · 30%

Hierarchy, composition, typography, color, polish, and coherent visual judgment.

Score9

Interaction & usability · 30%

Discoverability, responsiveness, feedback, control quality, and interaction feel.

Score7

Technical robustness · 30%

Runtime correctness, edge-case handling, performance, responsiveness, and code reliability.

Score8

Originality · 10%

Useful creative choices that go beyond a generic first solution without harming clarity.

Score8
03 / Run integrity

The claim, with its
conditions attached.

Model artifact1:18$0.1206 reported cost
Artifact score78/1006/6 requirements met
Protocolv0.7curated:orbit-radio:v2
Immutable attempts and publication recordInspect provenance

This Results Brief is rendered from a sanitized, allowlisted record rather than AI-authored article prose. Credentials, raw responses, generated source, executable artifacts, and private reviewer notes remain in the private Studio.

Run recordPR-MSTEDRD4-6F
Outcomesolo artifact
Test lineagev2 · curated:orbit-radio:v2
Identityrevealed
Evaluationlocked
Record hashsha256:9a9cb8e304668df1c0e4326fed62d124974a98dc50a5ab39ef900d92494db022
Immutable attempt ledger

A #1 original: completed submission (normal, OpenAI)

Download the hashed publication record ↓