handcrafted
Joined 6 months ago
Karma
5
Submissions
3
Member since
May 14
Recent submissions
Comment · 6 months ago
We have a section "How we compare to CadBench and BenchCAD" in our bench report comparing our Parametric CAD Bench with CADBench and BenchCAD: https://cadbench.ai/news/parametric-cad-bench
Comment · 6 months ago
GPT-5.5 and Opus 4.7 are comparable when using the same harness mini-swe-agent. GPT-5.5 demonstrates a significant performance delta only when integrated with the Codex module. We hypothesize that the superior performance of Opus 4.7 on mini-swe-agent relative to the more complex Claude Code harness stems from the tight feedback loop (edit-run-check), well suited for the CAD generation task.