Everything about Gemini 3 Flash Preview

What you need to know

Google DeepMind released Gemini 3 Flash Preview on December 17, 2025. It has a reasoning mode: it can "think" before answering, which helps with multi-step problems but uses more tokens, and therefore more money. It is a closed model: you access it through an API, from Google DeepMind or one of the 31 providers listed on models.dev. That makes it 10 months old as of October 22, 2026.

We file it under mid-range models (34 models in this category on the site).

What do independent benchmarks say?

According to results published by Epoch AI (checked on October 22, 2026), Gemini 3 Flash Preview has a capability index of 80.3 out of 100, computed on 5 benchmarks from our basket.

That puts it at #27 in our weekly model ranking.

• GPQA Diamond (PhD-level science questions): 89.4% — the best tracked model, Gemini 4 Argon, reaches 96.4%
• OTIS Mock AIME (competition mathematics problems): 95.6% — the best tracked model, GPT-5.5 Pro, reaches 100%
• FrontierMath (very hard research-level mathematics): 51.2% — the best tracked model, GPT-6 Astra, reaches 93.7%
• SWE-bench Verified (fixing real software bugs): 75.4% — the best tracked model, Claude Opus 4.7, reaches 83.5%

Context and capabilities

Its context window reaches 1,048,576 tokens, roughly 1,573 pages of text at 500 words per page: enough to load a whole book or a mid-sized codebase. A single answer can run to 65,536 tokens.

It accepts as input: text, image, video, audio and PDF. Its knowledge stops at January 2025: beyond that, it needs web search or your documents.

It can call tools (functions, APIs) and return structured JSON output, which makes it a possible foundation for an AI agent.

What it costs

Gemini 3 Flash Preview costs $0.50 per million input tokens and $3 per million output tokens (median of 31 providers, checked on October 22, 2026).

To put it in perspective: reading 20,000 tokens (about thirty pages) and writing 2,000 costs roughly $0.016; a thousand of those tasks, $16.

That is 1.5 times cheaper than the median output price of mid-range models ($4.38).

To estimate your own budget, use the agent cost calculator.

What is it good for?

Given its category, Gemini 3 Flash Preview is mainly aimed at a balance between quality and cost, for everyday uses that do not justify a frontier model.

Its SWE-bench Verified result (75.4%, above the median of tracked models) makes it a serious candidate for coding agents.

Its very large context window makes it worth considering for analysing large sets of documents in a single request.

Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.

Alternatives

In the same category, the models closest to Gemini 3 Flash Preview are:

• Grok 4.7 (xAI, index 79.9) — see the comparison
• Mistral Large 4 (Mistral AI, index 79.7) — see the comparison
• Claude Sonnet 5 (Anthropic, index 79.3)
• Gemini 3.1 Pro Preview (Google DeepMind, index 79.3)