What it measures
A language-model agent turns a written brief into an interactive three.js scene inside an offline environment.
How to read the result
This brings visual outcome and interactive behavior into coding evaluation; inspect the runnable artifact as well as its appearance.
Limits and comparison traps
This evaluates an LLM coding workflow. It does not evaluate an image-generation model or establish general software reliability.
Benchmark reference notes
Evaluates agents working in an offline sandbox (Stirrup) to build interactive 3D three.js scenes from written briefs.
Where this fits in an evaluation suite
The agent wrapper is part of the system. Pin tools, dependencies, timeouts, tests, and the repository revision. Compare contest coding separately from repository maintenance.
Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.
A reproducible comparison
Use the exact implementation, version, task subset, tool access, attempt budget, and judge described by the source.
Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.
PRIMARY EVIDENCE & FURTHER READING
Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.