grok · 2 arms · 3 effortscursor-grok-4.5

One model across every effort and arm. Each cell is a run — open it for the full card. Failure chips mark runs with no valid slot.

effort strip

arm \ effort
low
medium
high
cursor
cursor-grok-4.5 cursor lowopen run ↗
44.1K tokens4 runs · all valid
cursor-grok-4.5 cursor mediumopen run ↗
38.9K tokens4 runs · all valid
cursor-grok-4.5 cursor highopen run ↗
40.7K tokens4 runs · all valid
cursor-xl
cursor-grok-4.5 cursor-xl lowopen run ↗
40.6K tokens4 runs · all valid
cursor-grok-4.5 cursor-xl mediumopen run ↗
38.2K tokens4 runs · all valid
cursor-grok-4.5 cursor-xl highopen run ↗
40.7K tokens4 runs · all valid

effort → output size

Output completion tokens per effort, per arm. A read on how much each model spends as effort rises — not a quality axis.

025K50Klowmediumhigh
cursorcursor-xl
cursor-grok-4.5 — model · weather-card-benchmark