BenchCAD is now reported by a second frontier lab: OpenAI lists it in the GPT-5.6 launch table, next to OSWorld and BrowseComp — with Anthropic’s Claude system cards, that makes BenchCAD a benchmark both labs measure themselves against. Benchmark: benchcad.com.

BenchCAD scores for GPT-5.6 Sol, Luna, Terra and GPT-5.5, with and without a Python tool, as published in OpenAI's GPT-5.6 launch table BenchCAD rows from OpenAI’s GPT-5.6 launch table.