Canvas showed the animation immediately on load, with live preview available and the motion running in a continuous loop.
What was measured
In-Platform Preview
Real-time preview before export.
context, not decisivecapability
Previewing before export helps iterate, but it does not itself measure whether the tool can generate the animation correctly. (3 of 3 judges)
What was given, what came back
Test input: Search engines basics explainer · text
Input — what we sent
The exact prompt
Create an animation video explaining how search engines work.
A vague, linear educational animation prompt asking the tool to explain how search engines work with minimal guidance. Designed to stress inference, scene structuring, pacing, and coherent visual flow from an underspecified request.
Output — unretouched
ChatGPT Canvas — Screen Recording 2026-04-30 170046.mp4
Also checked on this input — same tool, 6 other criteria
Code Generation Quality✓ WorkedGenerated syntactically correct, runnable HTML/CSS/JavaScript on the first attempt for the search-engine explainer.Code Generation Quality✓ WorkedGenerates syntactically correct HTML/CSS/JavaScript on the first attempt and can produce an auto-playing, continuous-loop animation without user interaction.Output Quality◐ MixedCan match the requested topic, but the first-pass visual output is only a plain horizontal flowchart with text-only nodes, overflowing labels, and no icons or hierarchy, so it is not visually polished.Output Quality⚠ StruggledThe first-pass visual output was only a plain horizontal flowchart: text overflowed node boxes, there were no icons or visual hierarchy, and component differentiation was minimal.Output Quality⚠ StruggledThe initial output was a plain horizontal flowchart with text-only nodes; labels overflowed the node containers and there were no icons or visual hierarchy.Output Quality⚠ StruggledCan explain the search-engine pipeline accurately, but first-pass output is visually weak: a plain horizontal flowchart with overflowing node text, no icons, no visual hierarchy, and minimal differentiation between components.
Provenance
- Observation
- d60b7cdd-b974-41b0-bec9-1c6a3eee97b0
- Evidence run
- c751a76b-a105-4b3e-9ff3-6c4d6adc9f04
- Study
- Generate Code-based Animations from text inputs
- Research task
- 86b9nnzmy
- Tested at
- Jun 24, 2026
- Source
- first-party
- Evidence state
- observed
- Proof shown
- input + output shown
- Cost / latency
- not captured
- Repeat run
- not captured
- Tester
- not captured
The last three rows are honest blanks, not placeholders — our capture has no field for them yet.
Query this
get_evidence({
tool: "chatgpt-canvas"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 2 other tools
measured on In-Platform Preview
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com