A
BIM BENCHMARK / PILOT
Loading experiment…
Results could not be loaded. Refresh this page or check that the local server is running.
This experiment is planned.
No runs have been published yet.
Experiment results
Token usage
Recorded totals · cached input included
Click a bar to inspect its PDF. Includes agents where reported; other agent scopes are unknown. These snapshots measure recorded usage, not quality or billed cost.
Exact token counts & sources+
| Model · Effort | Total | Input | Cached input¹ | Output | Agent scope |
|---|
¹ Cached input is part of input; reasoning is part of output. — = unreported. * = arithmetic derivation. GPT-6 Sol · Ultra uses the reported combined total and combined cached count; input/output are unreported. Its separate chat-only snapshot is 7,119,141.
The drawings
The same selections as the graph above. Open a sheet to zoom or view the original PDF.
Full-sheet previews. Paper sizes vary; this is not a shared physical scale.
Side by side
B
The test prompt+
What this pilot can tell us+
One result per model and effort setting. The PDFs show the visible drawing; native element identity, editability and execution-rule compliance have not been verified. Token figures are snapshots, with differing agent scopes. No quality rankings, costs or run times are inferred.
Full method and future tests ↗