Skip to benchmark contentMotionBenchHosted by Baz Studio Human assessment
Pilot datasetOne prompt · one trial · 33 routes · not the official Core rankingRead the limits
anthropic · O+C
Claude Sonnet 4 6
claude-sonnet-4-6Pilot visual tierB
Dense prompt-fragment system resolves cleanly; slightly overfilled.
One diagnostic trial. This is not a durable model capability claim.