Gemini 3.5 Flash
Google · released May 19, 2026
Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...
Specification
- Context window
- 1.05M
- Max output
- 66K
- Knowledge cutoff
- Jan 1, 2025
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 2
- Moderated
- No
- Uptime
- 100.0%
Intelligence
52.0
96th percentile
Coding
70.1
Coding Index
Agentic
39.7
Agentic Index
Output speed
182 t/s
Median across providers
Latency
788ms
Time to first token
Cost per task
$0.79
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- τ²-bench (Telecom)95.3%
- GPQA Diamond92.2%
- AA-LCR (long context)81.0%
- IFBench76.3%
- SciCode53.1%
- Humanity's Last Exam42.7%
- Terminal-Bench Hard40.9%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| τ²-bench (Telecom) | 95.3% |
| GPQA Diamond | 92.2% |
| AA-LCR (long context) | 81.0% |
| IFBench | 76.3% |
| SciCode | 53.1% |
| Humanity's Last Exam | 42.7% |
| Terminal-Bench Hard | 40.9% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Muse Spark 1.1Meta53.2
- GPT-5.4OpenAI53.1
- GLM 5.2Z.ai52.6
- GPT-5.6 LunaOpenAI52.3
- Gemini 3.5 FlashGoogle52.0
- V4 Flash 0731DeepSeek51.8
- V4 Flash 0423DeepSeek51.8
- Gemini 3.6 FlashGoogle51.6
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Muse Spark 1.1 | 53.2 |
| GPT-5.4 | 53.1 |
| GLM 5.2 | 52.6 |
| GPT-5.6 Luna | 52.3 |
| Gemini 3.5 Flash | 52.0 |
| V4 Flash 0731 | 51.8 |
| V4 Flash 0423 | 51.8 |
| Gemini 3.6 Flash | 51.6 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $1.5
- Output / 1M tokens
- $9
- Cached input / 1M
- $0.15
- Blended 3:1
- $3.38
One task, estimated
$0.79
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.
Arena
Head-to-head generation quality
Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.
- Overall Elo
- 1,309
- Win rate
- 56.8%
- Strongest at
- UI components
- Tournaments
- 2,151
Elo by category
Dot position on a 1,200–1,325 scale · Elo has no meaningful zero
- 1,309
- 1,309
- 1,296
- 1,295
- 1,282
- 1,262
- 1,234
- 1,218
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| UI components | 1309 | 56.8% |
| Game development | 1309 | 56.5% |
| SVG | 1296 | 60.9% |
| 3D scenes | 1295 | 57.7% |
| Websites | 1282 | 55.3% |
| Data visualisation | 1262 | 54.8% |
| Full-stack apps | 1234 | 56.7% |
| Mobile apps | 1218 | 53.5% |