ModelBenchmarkScoreSourceChecked
GPT-6 AstraOSWorld72.6%Source ↗
GPT-6 AstraSWE-bench Verified80.4%Source ↗
GPT-6 AstraAutomationBench41.4%Source ↗
Claude Sonnet 4.6SWE-bench Verified77.2%Source ↗

Methodology

Scores are copied from the vendor or harness page linked per row. They are point-in-time snapshots for comparing local models against hosted references, not targets to match on-device. Rows are re-checked weekly; any row older than ten days is flagged for refresh.