Gemini 3 Flash Preview benchmarks, pricing and specs
Gemini 3 Flash Preview is a Google model released on December 17, 2025 that takes text, image, audio and video input and produces text. It costs $0.50 per 1M input tokens and $3 per 1M output tokens and accepts up to 1,048,576 tokens of context. It scores 1473 Elo on Arena Text, #21 of 39 current models (Arena, measured October 8, 2026).
- Per 1M input tokens
- $0.50
- Per 1M output tokens
- $3
- Context window
- 1.05M
- Arena Text
- 1473 Elo · #21/39
Data verified October 12, 2026 · Dataset 2026-10-12
Key facts
- Provider
- Model family
- Gemini 3
- Release date
- December 17, 2025
- Status
- Current
- Access
- API only
- API model id
- Not reported
- Context window
- 1,048,576 tokens
- Max output
- 65,536 tokens
- Input
- text, image, audio, video
- Output
- text
- Task families
- text, multimodal
- Declared capabilities
- reasoning, coding, agentic coding
Gemini 3 Flash Preview pricing
It is the #9 cheapest of 37 current text models priced per 1M input tokens.
Independent benchmark results
Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. Google's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.
| Benchmark | Score | Rank | Measured | Source |
|---|---|---|---|---|
| Arena Text | 1473 Elo | #21 of 39 | October 8, 2026 | Arena · 2026-10-12 |
| GPQA Diamond | 89.4% | #27 of 37 | October 12, 2026 | Epoch AI · 2026-10-12 |
| FrontierMath Tiers 1-3 (v2) | 51.2% | #30 of 37 | October 12, 2026 | Epoch AI · 2026-10-12 |
| SimpleQA Verified | 66.8% | #10 of 34 | October 12, 2026 | Epoch AI · 2026-10-12 |
Strengths, cautions and best uses
Strengths
- Google documents multimodal inputs, thinking, computer use, code execution, and function calling
Cautions
- This preview endpoint may change before becoming stable and the published price varies by input modality
Best for
- Fast multimodal and agentic coding evaluations
Alternatives to Gemini 3 Flash Preview
The closest current textmodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.
Cheaper, same or higher score
DeepSeek-V4.1-Flash
- 40% cheaper per 1M input tokens, $0.30 vs $0.50
- 2 points higher on Arena Text, 1475 vs 1473
- From DeepSeek
GPT-4.1 mini
- 20% cheaper per 1M input tokens, $0.40 vs $0.50
- 90 points lower on Arena Text, 1383 vs 1473
- From OpenAI
Gemini 3.7 Flash
- 50% more per 1M input tokens, $0.75 vs $0.50
- 13 points higher on Arena Text, 1486 vs 1473
Gemini 3.8 Flash
- 50% more per 1M input tokens, $0.75 vs $0.50
- 24 points higher on Arena Text, 1497 vs 1473
Compare Gemini 3 Flash Preview with
Gemini 3 Flash Preview FAQ
How much does Gemini 3 Flash Preview cost?
Gemini 3 Flash Preview costs $0.50 per 1M input tokens and $3 per 1M output tokens at the standard tier. It is the #9 cheapest of 37 current text models priced per 1M input tokens. Source: Google, verified October 11, 2026.
What is the context window of Gemini 3 Flash Preview?
Gemini 3 Flash Preview accepts up to 1,048,576 tokens of context. It can return up to 65,536 tokens in one response. That ranks #10 of 44 current text models by context length.
How does Gemini 3 Flash Preview score on independent benchmarks?
Gemini 3 Flash Preview scores 1473 Elo on Arena Text, #21 of 39 current models (Arena, measured October 8, 2026), 89.4% on GPQA Diamond, #27 of 37 current models (Epoch AI, measured October 12, 2026) and 51.2% on FrontierMath Tiers 1-3 (v2), #30 of 37 current models (Epoch AI, measured October 12, 2026). These are independent evaluations, not Google's own launch figures.
Is Gemini 3 Flash Preview open source or API only?
Gemini 3 Flash Preview is available through Google's API only; its weights are not published.
What are the best alternatives to Gemini 3 Flash Preview?
The closest current alternatives by price and measured performance are DeepSeek-V4.1-Flash (40% cheaper per 1M input tokens, $0.30 vs $0.50), GPT-4.1 mini (20% cheaper per 1M input tokens, $0.40 vs $0.50), Gemini 3.7 Flash (50% more per 1M input tokens, $0.75 vs $0.50) and Gemini 3.8 Flash (50% more per 1M input tokens, $0.75 vs $0.50).
Sources
- Gemini 3 Flash Preview · Google · official · verified August 18, 2026 · CC-BY-4.0
- Gemini deprecations · Google · official · verified August 18, 2026 · CC-BY-4.0
- Gemini Developer API pricing · Google · official · verified October 11, 2026
- Epoch AI Benchmarking Hub data (benchmark_data.zip) · Epoch AI · independent · verified October 12, 2026 · CC-BY-4.0
- Arena leaderboard dataset (lmarena-ai/leaderboard-dataset) · Arena · independent · verified October 12, 2026 · CC-BY-4.0
Cite this page
Van Data Team. "Gemini 3 Flash Preview Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-12. https://vandatateam.com/ai-model-benchmarks/gemini-3-flash-preview
Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.
Production evaluation
Deciding whether Gemini 3 Flash Preview fits your workload?
Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- Evaluation cases and acceptance thresholds tied to real work
- Model routing, fallbacks and cost controls