deepseek · 1 arm · 6 effortsdeepseek-v4-flash-0731

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
minimal
low
medium
high
max
api
deepseek-v4-flash-0731 api noneopen run ↗
29K tokens8 runs · all valid
deepseek-v4-flash-0731 api minimalopen run ↗
149.7K tokens8 runs · all valid
deepseek-v4-flash-0731 api lowopen run ↗
124.1K tokens8 runs · all valid
deepseek-v4-flash-0731 api mediumopen run ↗
318.6K tokens7 of 8 valid
deepseek-v4-flash-0731 api highopen run ↗
245.1K tokens7 of 8 valid
deepseek-v4-flash-0731 api maxopen run ↗
263.5K tokens8 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.

API
11.0×none → medium output
0250K500Knoneminimallowmediumhighmax318.6K29K
deepseek-v4-flash-0731 — model · weather-card-benchmark