claude · 2 arms · 5 effortsclaude-fable-5-thinking

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
cursor
claude-fable-5-thinking cursor lowopen run ↗
14.6K tokens4 runs · all valid
claude-fable-5-thinking cursor mediumopen run ↗
23.4K tokens4 runs · all valid
claude-fable-5-thinking cursor highopen run ↗
34K tokens4 runs · all valid
claude-fable-5-thinking cursor xhighopen run ↗
77.3K tokens4 runs · all valid
claude-fable-5-thinking cursor maxopen run ↗
162K tokens4 runs · all valid
cursor-xl
claude-fable-5-thinking cursor-xl lowopen run ↗
14.9K tokens4 runs · all valid
claude-fable-5-thinking cursor-xl mediumopen run ↗
23.2K tokens4 runs · all valid
claude-fable-5-thinking cursor-xl highopen run ↗
31.2K tokens4 runs · all valid
claude-fable-5-thinking cursor-xl xhighopen run ↗
78.8K tokens4 runs · all valid
claude-fable-5-thinking cursor-xl maxopen run ↗
228.5K 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.

15.3×low → max output
0250K500Klowmediumhighxhighmax228.5K14.9K
cursorcursor-xl
claude-fable-5-thinking — model · weather-card-benchmark