Benchmark menu

Model detail

Gemini 3.5 Flash

A static, shareable model page that remains complete without JavaScript.

Model detail

Gemini 3.5 Flash

Provider: Google · Public slug: google-gemini-3-5-flash

Compare in Charts View game entrants Leaderboard

Rank: 7
Rank movement: Baseline
Score: 44.5
Last measured: 2026-07-05
Coverage: None not supported

Reasoning scores

XHigh: 38.8
Medium: 50.3
None: —

Generation health

XHigh0%75%25%n 8Medium0%100%0%n 8 None not supportedHigh repair rateHigh failure rate

Cost summary

Mean standard list-price equivalent: $0.42
Median unique-cell cost: $0.40
Unique-cell range: $0.25–$0.69
Coverage: 16 unique cells / 16 observed runs
Observed-run total: $6.70
Evidence basis: Provider-reported
Mean output: 43k tok
Output range: 26k–74k tok
Token samples: 16

Cost means equal-weight unique model/game/reasoning cells. Provider-account billed spend is reported separately on Charts.

Run setup

Overall Models: combines public reasoning variants
Standard GameBench code-generation prompt