Google model product
Gemini 3.6 Flash
6 Flash is Google's workhorse multimodal reasoning model for agentic coding, knowledge work, and spatial reasoning.
Updated Aug 12, 2026. Default version: Gemini 3.6 Flash
LLMBoard score79.3Gemini 3.6 Flash
Coverage20%6 benchmark families
Context window1MTokens
Official input price$1.5Google API
Gemini 3.6 Flash Specifications
Technical details for the model's default version.
- Version
- Gemini 3.6 Flash
- Released
- Jul 21, 2026
- Knowledge cutoff
- Mar 31, 2026
- Parameters
- N/A
- Context window
- 1M
- Max output
- 65.5K
- Inputs
- audio, image, pdf, text, video
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Gemini 3.6 Flash Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemini 3.6 Flash Benchmark Results
Benchmark scores for Gemini 3.6 Flash.
| MLE-Bench | 63.9% | 01 | 2 | 100.0% | C | |
| OSWorld-Verified | 83.0% | 04 | 23 | 86.4% | C | |
| CharXiv-R | 89.4% | 05 | 48 | 91.5% | C | |
| MRCR v2 (8-needle) | 54.0% | 07 | 21 | 70.0% | C | |
| Terminal-Bench 2.1 | 78.0% | 12 | 19 | 38.9% | C | |
| DeepSWE 1.1 | 49.0% | 15 | 20 | 26.3% | B | |
| SWE-Bench Pro | 58.7% | 15 | 45 | 68.2% | C |
Gemini 3.6 Flash Arena Results
Preference and agent-evaluation results for the default version.
| vision style control | overall | 07 | 1294.7 | 1,205 | N/A | |
| vision | overall | 08 | 1310.9 | 1,205 | N/A | |
| text | overall | 13 | 1479.1 | 13,123 | N/A | |
| text style control | overall | 15 | 1483.6 | 13,123 | N/A | |
| agent tool hallucination | overall | 18 | 0.0 | N/A | 384K | |
| text factuality | overall | 18 | 1473.1 | 13,123 | N/A | |
| webdev | overall | 18 | 1536.2 | 5,052 | N/A | |
| agent task outcome explicit | overall | 30 | -0.0 | N/A | 6K | |
| agent praise complaint | overall | 33 | -0.1 | N/A | 2.3K | |
| agent | overall | 35 | -0.0 | N/A | 422.6K | |
| agent steerability | overall | 35 | -0.0 | N/A | 8.8K | |
| agent bash recovery steps | overall | 36 | -0.0 | N/A | 21.5K |
Gemini 3.6 Flash Runtime Performance
Provider-specific output speed and catalog latency for Gemini 3.6 Flash. Runtime does not affect the capability score.
| 6.866 tok/s | 29.647 s | 1M | 65.5K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Gemini 3.6 Flash Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1.5 input, $7.5 output per 1M
- Official provider
- Lowest third-party
- From $1.5 input, $7.5 output per 1M via Impossibl
- Tracked offerings
- 17
| Impossibl | google/gemini-3.6-flash | global | $1.5 | $7.5 | 1M | |
| CrossModel | gemini/gemini-3.6-flash | global | $1.5 | $7.5 | 1M | |
| gemini-3.6-flash | global | $1.5 | $7.5 | 1M | ||
| NanoGPT | google/gemini-3.6-flash | global | $1.5 | $7.5 | 1M | |
| LLM Gateway | gemini-3.6-flash | global | $1.5 | $7.5 | 1M | |
| OpenCode Zen | gemini-3.6-flash | global | $1.5 | $7.5 | 1M | |
| GitHub Copilot | gemini-3.6-flash | global | $1.5 | $7.5 | 1M | |
| Neon | gemini-3-6-flash | global | $1.5 | $7.5 | 1M | |
| Pioneer | gemini-3.6-flash | global | $1.5 | $7.5 | 1M | |
| Ofox | google/gemini-3.6-flash | global | $1.5 | $7.5 | 1M | |
| Vertex | gemini-3.6-flash | global | $1.5 | $7.5 | 1M | |
| Requesty | gemini-3.6-flash | global | $1.5 | $7 | 1M | |
| Kilo Gateway | google/gemini-3.6-flash | global | $1.5 | $7.5 | 1M | |
| Merge Gateway | google/gemini-3.6-flash | global | $1.5 | $7.5 | 1M | |
| Vercel AI Gateway | google/gemini-3.6-flash | global | $1.5 | $7.5 | 1M | |
| OpenRouter | google/gemini-3.6-flash | global | $1.5 | $7.5 | 1M | |
| Venice AI | gemini-3-6-flash | global | $1.88 | $9.38 | 1M |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Gemini 3.6 Flash Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Gemini 3.6 Flash | 79.3 | N/A | 1M | 65.5K | No | Proprietary |
What is Gemini 3.6 Flash?
Key information about Gemini 3.6 Flash and its available data.
6 Flash is Google's workhorse multimodal reasoning model for agentic coding, knowledge work, and spatial reasoning. It supports text, image, video, audio, and PDF inputs, a 1 million-token context window, and a 65,536-token text output. 5 Flash.
Data as of 2026-08-11.
Gemini 3.6 Flash vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Gemini 3.6 Flash
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemini 3.5 Flash
GOGoogle
Gemini 3.1 Pro
GOGoogle
Gemini 3.5 Flash Cyber
GOGoogle
Gemini 3 Pro
GOGoogle
Gemini 3 Flash
GOGoogle
Gemma 4 31B
FAQ
Common questions about Gemini 3.6 Flash.
When was Gemini 3.6 Flash released?
Gemini 3.6 Flash's default version was released on Jul 21, 2026.
How much does Gemini 3.6 Flash cost?
Gemini 3.6 Flash's official API price is $1.5 per million input tokens and $7.5 per million output tokens via Google. The lowest tracked third-party offer starts at $1.5 input and $7.5 output via Impossibl.
Who created Gemini 3.6 Flash?
Gemini 3.6 Flash was created by Google.
What is the context window for Gemini 3.6 Flash?
The default version has a 1M token context window.
Is Gemini 3.6 Flash open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Gemini 3.6 Flash?
17 provider offerings are linked to the default version.
What models should I compare Gemini 3.6 Flash with?
Nearby ranked alternatives include Muse Spark 1.2, Grok 4.5, Claude Opus 4.6.