Perceptron Mk1.5, an embodied reasoning model that Perceptron built for robots and other physical agents, scored 73.7 on the Great Commission Benchmark in a run completed October 10, 2026. Across 150 prompts it accepted 96, compromised 29, and refused 25. That is the highest score in this round of r

In the last 30 days on the Great Commission Benchmark, we spotlight two models with the strongest **overall scores** among new publications.

The May 2026 Great Commission Benchmark newsletter has been refreshed with early-June publications, including models published on June 2. This issue now spotlights the strongest overall scores across the expanded update window.

perceptron/perceptron-mk1 scored 71.0 on GCB v1.0.0, with 93 accepted, 27 compromised, and 30 refused responses.