claude · 1 arm · 5 effortsclaude-opus-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
xhigh
max
CC
claude-opus-5 CC lowopen run ↗
23.2K tokens4 runs · all valid
claude-opus-5 CC mediumopen run ↗
34.2K tokens4 runs · all valid
claude-opus-5 CC highopen run ↗
55.6K tokens4 runs · all valid
claude-opus-5 CC xhighopen run ↗
108.8K tokens4 runs · all valid
claude-opus-5 CC maxopen run ↗
210.8K 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.

claude-code (CLI)
9.1×low → max output
0125K250Klowmediumhighxhighmax210.8K23.2K
claude-opus-5 — model · weather-card-benchmark