Benchmark
Which model reviews best, and what it costs
Nothing measured since 2026-08-15
Nothing measured since 2026-08-15
This page draws what has been measured since 2026-08-15 and fills in as runs are recorded.
How these models were measured
Which harness a model ran under is a variable held beside it, not the thing this page compares. These sections read the harness: what it costs to find a blocking defect with one, how each has moved campaign by campaign, and what every configuration of one was priced at.
Cost of a blocking defect, by harness
Cheapest first · 0 of 0 defects are merge-blocking · no campaign since 2026-08-15No harness has been measured since 2026-08-15
Record a native run to see per-harness cost and detection here.