GoogleProvisional

Gemini 3.5 Flash

Gemini 3.5 / Flash · gemini-3.5-flash

Google fast multimodal model for broad agent and long-context developer workflows.

Objective score

33.6

Confidence

79%

Price evidence

Pricing evidence pending

Support this model Compare trend Official source

Other primary tiers in this family

FlashFlash Lite

Scenario evidence

Six task-specific rankings

Feature development#37Obj. 33.60 · 0%Debug and repair#22Obj. 52.40 · 0%Refactoring#20Obj. 52.40 · 0%Code review#17Obj. 54.40 · 0%Large-repo agent work#38Obj. 28.60 · 0%Frontend / UI#18Obj. 52.40 · 0%

Evidence state

Signal coverage

Benchmarks: 2
Rank points: 7
Usage: 2
Agent: 0
Sources: 6

Objective evidence

Benchmarks and public signals

Swebench: —
Livecodebench: —
Aider: —
Artificial Analysis: 70.1
Openrouter Usage: 1.6
Kilo Usage: —

Persistent history

Recent ranking points

Aug 1#38 · 36

Aug 1#38 · 36

Jul 31#37 · 36

Jul 31#37 · 36

Jul 31#37 · 36

Jul 31#37 · 36

Usage signals

OpenRouter1.6%

Overall1.1%

Agent and tool signals

Evidence is being collected. Missing data is not treated as zero.

Source trail

Official Gemini API models page documents current Gemini model naming and lifecycle.Artificial Analysis Coding Agents · ok WebDev Arena · ok Kilo leaderboard · ok Gemini API models · ok Gemini 3.1 Pro Preview model page · ok Gemini 3.5 Flash model page · ok