gemini · 3 arms · 4 effortsgemini-3.6-flash

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
minimal
low
medium
high
api
gemini-3.6-flash api minimalopen run ↗
50.9K tokens8 runs · all valid
gemini-3.6-flash api lowopen run ↗
37K tokens8 runs · all valid
gemini-3.6-flash api mediumopen run ↗
62.1K tokens8 runs · all valid
gemini-3.6-flash api highopen run ↗
81.7K tokens8 runs · all valid
cursor
gemini-3.6-flash cursor minimalopen run ↗
43.2K tokens4 runs · all valid
gemini-3.6-flash cursor lowopen run ↗
38.7K tokens4 runs · all valid
gemini-3.6-flash cursor mediumopen run ↗
131K tokens4 runs · all valid
gemini-3.6-flash cursor highopen run ↗
156.6K tokens4 runs · all valid
cursor-xl
no valid slot
no valid slot0 of 4 valid
gemini-3.6-flash cursor-xl lowopen run ↗
30.6K tokens4 runs · all valid
gemini-3.6-flash cursor-xl mediumopen run ↗
97.2K tokens4 runs · all valid
no valid slot
no valid slot0 of 4 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.

4.0×low → high output
0100K200Kminimallowmediumhigh156.6K38.7K
APIcursorcursor-xl
gemini-3.6-flash — model · weather-card-benchmark