Google: Gemini 3 Flash Preview
Analysis Summary
Google Gemini 3 Flash Preview sits at an intelligence index of 37.8, placing it in the very strong tier just below the top flagship models. Its coding performance is exceptional for a Flash-class model, with livecodebench at 0.908 and a math index of 97. The agentic index of 59.5 and tau2 of 0.804 confirm reliable multi-step task handling. The 1M token context window is a major practical advantage for long-document and codebase analysis.
For businesses, this model covers a wide range of workloads: software engineering assistance, autonomous agents, long-document analysis, and multimodal content tasks (image, audio, video, file input all supported). Instruction following (ifbench 0.780) and long-context reasoning (lcr 0.663) are both strong. The main trade-off is pricing: at $0.50 input and $3.00 output, it is not the cheapest Flash-tier option.
Teams needing broad capability breadth, a massive context window, and multimodal input in a single model will find Gemini 3 Flash Preview a strong fit. It is a Google-backed model with full enterprise support, making it a low-risk production choice.
Assessed June 30, 2026
Editorial notes
Gemini 3 Flash Preview from Google delivers near-frontier reasoning with a 1M token context, full multimodal input (image, audio, video, file), and strong coding and agentic scores at a competitive price for its capability tier.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Google: Gemini 3 Flash Preview compares
Google: Gemini 3 Flash Preview ranks #42 of 385 AI models we track for overall intelligence, #64 of 293 for agentic tasks. Its 1M-token context window is larger than 97% of the models we list. At $0.50 per million input tokens it is cheaper than 35% of comparable models.
About Google: Gemini 3 Flash Preview
Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Google: Gemini 3 Flash Preview stack up?
Compare side-by-side with other professional models.
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.50 | $0.000500 |
| Output | $3.00 | $0.003000 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Google: Gemini 3 Flash Preview
How much does Google: Gemini 3 Flash Preview cost?
Google: Gemini 3 Flash Preview costs $0.50 per million input tokens and $3.00 per million output tokens.
What is the context window of Google: Gemini 3 Flash Preview?
Google: Gemini 3 Flash Preview has a context window of 1,048,576 tokens (1M).
What can Google: Gemini 3 Flash Preview do?
Google: Gemini 3 Flash Preview supports image/vision input, tool use, and function calling.
Who created Google: Gemini 3 Flash Preview?
Google: Gemini 3 Flash Preview is developed by Google and was released on December 17, 2025.
