claude · 3 arms · 1 effortclaude-sonnet-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
none
cursor
claude-sonnet-4-5 cursor noneopen run ↗
11.4K tokens4 runs · all valid
cursor-xl
claude-sonnet-4-5 cursor-xl noneopen run ↗
10.9K tokens4 runs · all valid
kiro
claude-sonnet-4-5 kiro noneopen run ↗
— 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.

010K20Knone
cursorcursor-xlkiro
claude-sonnet-4-5 — model · weather-card-benchmark