Gemini 3.6 Flash (high)
Gemini 3.6 Flash delivers higher quality across coding, agentic workflows, and web development with reduced token consumption and fewer model calls compared to previous model iterations.
Introducing Gemini 3Model Snapshot
TypeLanguage
ReleaseJul 21, 2026
Context1,048,576
Tagsreasoning, file-input, tool-use, vision
Overall
Rank #34 across 600
50.1
Coding
Rank #38 across 266
69.2
Blended Price
Rank #264 across 379
$3.00/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed230.4 tok/s
First Token13.24s
Max Output65,536
Pricing
Blended$3.00/M
Input$1.50/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 50.1 | #34 |
| Artificial Analysis Coding Index | coding | 69.2 | #38 |
| LiveBench Mathematics | math | 86.4% | #18 |
| GPQA | reasoning | 92.8% | #12 |