Benchmark menu

Model detail

Gemini 3.1 Flash Lite

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

Model detail

Gemini 3.1 Flash Lite

Provider: Google · Public slug: google-gemini-3-1-flash-lite

Compare in Charts View game entrants Leaderboard

Rank: 31
Rank movement: Baseline
Score: 17.0
Last measured: 2026-07-05
Coverage: Complete coverage

Reasoning scores

XHigh: 21.7
Medium: 19.3
None: 10.1

Generation health

XHigh0%63%37%n 8Medium25%50%25%n 8None38%25%37%n 8 Complete coverageHigh repair rateHigh failure rate

Cost summary

Mean standard list-price equivalent: $0.01
Median unique-cell cost: $0.01
Unique-cell range: $0.0034–$0.04
Coverage: 24 unique cells / 24 observed runs
Observed-run total: $0.35
Evidence basis: Provider-reported
Mean output: 6.8k tok
Output range: 931–23k tok
Token samples: 24

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