BenchLeader
GoogleReasoning modelAuto-detected

Gemini 2.5 Computer Use 10

Not yet ranked: too few independent results so far. Released 7 Oct 2025.

Blended price
$3.44/M
$1.25 in · $10.00 out
Output speed
First answer
Context
131k

No independent quality benchmark results yet — only pricing and metadata.

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.0035
Summarise a 30-page report12,000 / 600$0.021
Code edit6,000 / 1,500$0.022
Agentic coding session60,000 / 4,000$0.115
Structured extraction2,000 / 200$0.0045

See also

Data as of 9 Sept 2026. Compare with another model.