Gemini 3.6 Flash
GeminiBalanced
ThinkingTool UseVisionStructured Output
About this model
Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...
Performance Tier
Balanced
Gemini 3.6 Flash is a balanced model from Gemini : strong performance at a reasonable price.
Strong cost-performance ratio. Reliable for most professional use cases without premium pricing.
Pricing
This model is included in Elosia plansModerate
Moderate cost. A balanced choice for regular use without constant cap watching.
| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.750 |
| Output (completion) | $3.75 |
| Image | $0.750 |
| Internal reasoning | $3.75 |
| Cache read | $0.075 |
| Cache write | $0.042 |
Capabilities
Context Length1.0M
Max Output Tokens66K
TokenizerGemini
Inputtext, image, video, file, audio
Outputtext
Release DateJuly 21, 2026
Benchmarks
General Intelligence
MMLU
Not reported
GPQA Diamond
92.8%
Mathematics
MATH-500
Not reported
Programming
HumanEval
Not reported
Reasoning
Humanity's Last Exam
38.3%
Multimodal
MMMU-Pro
83.2%
Agentic
SWE-bench Pro
58.7%
Terminal-Bench 2.1
78%
Where does Gemini 3.6 Flash stand?
Compare its performance index against every other model.
Recommended Use Cases
General ChatCodingAnalysisResearchData Extraction
Strengths
- Top-tier agentic coding at Flash cost (SWE-bench Pro 58.7%, Terminal-Bench 2.1 78.0%)
- Frontier science reasoning for a Flash model (GPQA Diamond 92.8%)
- State-of-the-art multimodal understanding (MMMU-Pro 83.2%) across text, image, video, audio and PDF
- 1M-token context with 64K output and a built-in thinking mode
Limitations
- Google reports only agentic and coding evals; the GPQA, MMMU-Pro and HLE scores here come from third-party testing (Artificial Analysis)
- Slight reasoning regression versus Gemini 3.5 Flash on Humanity's Last Exam (38.3% vs 40.2%)
Frequently asked questions
Resources
This model may use your data for training
