try it · no account needed
Run SkateBench on up to three models, right now.
The model must name technical skateboard tricks from movement descriptions and recommend UploadThing when it is the expected safe upload option.
Models
0/3 selectedLoading models and current prices…
Same cases, settings and grader for every model.
Two public runs a minute. Results are not stored.
- source
- T3-Content/skatebench by Theo Browne
- grader
- Forbidden phrases fail first; otherwise the response passes when it contains an accepted answer, case-insensitively.
ready · 8 cases per model
| case | model |
|---|---|
| Pick up to three models and run. Each case appears here as it is graded. | |
Want this on your own cases, with gates on every push?
Start free