15 and 33 million triangles, measured

Can an open-source sculpting app handle high-poly work? Don't take our word for it. These are SculptForge's own numbers on a 15 and a 33 million triangle head, from a benchmark anyone can run with one command, on the same scene with the same strokes. Run it on your computer and compare.

Run it yourself in 3 steps

Get SculptForge
Install the latest release (free, Linux, macOS, Windows). Close anything heavy: builds, games, renders.
Run the standard scene
Help > Benchmark, choose Standard 15M or 33M, Start. Or from a terminal:
```
sculptforge --benchmark standard-15m
sculptforge --benchmark standard-33m
```
Read the result
About a minute per size. A table shows the numbers; a JSON file and an MP4 of the run (with the numbers on screen) are saved. Send the JSON to be listed here.

The scene. A procedural head (skull, brow, nose, jaw, ears) built from a formula, so it's identical everywhere, with subdivision levels: about 15 or 33 million triangles. A scripted pen stroke (a figure eight, 240 pointer samples a second) goes through the same code a real pen does, with each brush in turn: Clay at 25, 60 and 120 px, Move (80 px), Smooth (60 px) and a 240 px Clay brush, then an orbit. Vertical sync off; the window size used is in each result.

The numbers. Frame p50 / p95 / p99: time per frame, the median and the slow ones you'd feel (16.7 ms is 60 fps). Lag: how far the stroke on screen trails the pointer, in pixels along the path. Worst stall: the longest the screen froze, including lifting the pen. Peak RAM: the most memory SculptForge held; GPU: its vertex and index buffers (on unified-memory machines like Apple silicon these share RAM). Lower is better everywhere.

Results

Scene Stroke

Machine	OS	Processor	Graphics	RAM	Build	fps	Frame p50	p95	p99	Lag p50	p95	Worst stall	Peak RAM	GPU	Video
Loading results...

Worst stall, peak RAM and GPU memory are for the whole run of that size (every stroke). Colours: green within a 60 Hz frame (16.7 ms), amber within two, red slower. Raw data: results.json.

Submit your result

The easy way: an issue

Open a Benchmark result issue, describe the computer, and paste the JSON file. We check it and add it here.

The direct way: a pull request

From a clone of the repository:

python3 tools/benchmark/submit.py check result.json
python3 tools/benchmark/submit.py add result.json \
  --name "your handle" --machine "laptop model" \
  --video https://...

and open a pull request with the change to website/benchmarks/results.json.

SculptForge itself uploads nothing: the benchmark only writes files on your computer. The format: docs/benchmark.md.

Comparing with other apps

This page lists SculptForge results only. We don't run, publish or test against other sculpting applications' numbers or output. If you use another app, sculpt a similar mesh there and judge for yourself.