Skip to content
ModelCap

Gemini 3 Flash Preview

Arena #45No linked weights

Google·#45 of 504 in the all-versions archive

Gemini 3 Flash Preview is a language model from Google. It ranks #45 of 504 in ModelCap's all-versions archive, with an Index score of 77.2, measured on 3 public benchmarks. Its score range of 72.3–82.1 spans positions #12–#74. It is listed at $0.50 per million input tokens and $3.00 per million output tokens across 2 providers. It reads up to 1M tokens of context, with no downloadable weights linked in the current source data.

Figures as of 6 Nov 2026, 13:52 UTC · download the public dataset · methodology

ModelCap Index · All-versions archive
77.2#45
Measured on 3 public benchmarks · range 72.3–82.1
Evidence as of 4 Nov 2026, 23:07 UTC
Market Gravity
52.5Decreased by 0.1
Secondary market signal

Superseded by Gemini 3.8 Flash. It no longer holds a current-board position; its all-versions archive rank is #45.

Input
$0.50
per 1M tokens
Output
$3.00
per 1M tokens
Context
1M
tokens
Providers
2
6 endpoints

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Googleglobal/flexCheapest$0.25$1.501M—0.00%
Google AI Studioflex$0.25$1.501M—100.0%
Googleglobal$0.50$3.001M—100.0%
Google AI Studio$0.50$3.001M—100.0%
Googleglobal/priority$0.90$5.401M—100.0%
Google AI Studiopriority$0.90$5.401M—100.0%

Reasoning efforts

Best supported result can inform ModelCap

Published Max, X-High, High and other configurations for this model. These are sourced scores, not head-to-head essays.

Related community configurations

Human preference rating
ConfigurationRatingSource rankVotesSource
Minimal
Gemini 3 Flash (Minimal)
1458
CI 1455–1461
#6391KLMArena
Match 98%

Other versions (5)

ModelCap Index · All-versions archive

Methodology
77.2
Measured on 3 public benchmarks
All-versions archive
#45 of 504
Score range
72.3–82.1
Rank range
#12–#74
Evidence as of
4 Nov 2026, 23:07 UTC
Benchmarks used
ARC-AGI-2 Verified, Arena Coding, Arena Overall
Technical details
Public rank basis
Measured (measured)
Evidence label
Measured · 3 public benchmark observations across 3 boards
Index support
64.0% · strong
Identity binding
Exact catalogue product · google/google/gemini-3-flash-preview · aggregates disclosed benchmark configurations · endpoint configuration not claimed
Index observations used
3
Qualified Index evidence point
77.2
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
77.2
Evidence status
confirmed · 87% mass
General preference
78.8
Coding
71.3
Agents & tools
—
Reasoning
34.0
Evidence breadth
95%
Evidence coverage
64%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
37.6
Liquidity (providers × uptime)
91.5
Open reach (HF downloads)
—
Surface (context / tools / modalities)
100.0
Freshness
29.1
  • · OpenRouter popularity #38
  • · 2 live providers
  • · Catalogue: context 1048576, reasoning, tools, modalities Text/Image/File/Audio/Video
  • · First seen 2025-12-17

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
45.3
partial · 56% metadata coverage
Not capability
Artifact reproducibility
0.0
Access & legal clarity
30.3
Deployability
80.0
Evaluation provenance
76.3

Not yet published: a pinned repository revision, the architecture and model type, a parameter count, safetensors weight metadata, the base model it derives from, a declared licence, a link to the licence terms, pinned evaluation dataset versions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
52.5
OpenRouter weekly popularity
#38 of 339

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
LMArena
Official rank
#45 of 419
Rating
1472.7
95% confidence interval
1468–1477
Votes
31K
Source published at
28 Oct 2026, 00:00 UTC
Category
overall
Identity match confidence
98%

Market Gravity breakdown

Usage55%
37.6

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
91.5

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
50.0

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
29.1

Time since first public availability, on a six-month half-life.

Specification

Model ID
google/gemini-3-flash-preview
Context window
1M tokens
Declared output cap
66K tokens

OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. OpenRouter metadata

Inputs
Text, Image, File, Audio, Video
Outputs
Text
Tokenizer
Gemini
Cached input tokens
$0.05 / 1M
First seen on OpenRouter
17 Dec 2025

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated

Benchmark leaderboards featuring Gemini 3 Flash Preview

All leaderboards
Public benchmark boards on which Gemini 3 Flash Preview has a published result
LeaderboardScoreSource rankConfigurationPublished
Arena text leaderboardArena (LMArena)14731468–1477#45 of 419Not reported28 Oct 2026
Arena coding leaderboardArena (LMArena)15051497–1513#68 of 414Default28 Oct 2026
ARC-AGI-2 leaderboardARC Prize Foundation33.6%#124 of 280High4 Nov 2026
SWE-bench leaderboardSWE-bench (Princeton / SWE-agent team)75.8%#2 of 47High17 Feb 2026

Gemini 3 Flash Preview: common questions

How does Gemini 3 Flash Preview rank among AI models?

Gemini 3 Flash Preview is a superseded version and is not on the current board as of 6 November 2026. Its archive position, where one exists, is shown on the page; the newer version carries the current rank.

How much does Gemini 3 Flash Preview cost per 1M tokens?

Gemini 3 Flash Preview is listed at $0.50 per 1M input tokens and $3.00 per 1M output tokens as of 6 November 2026; the lowest output price among 2 providers is $1.50 on Google. Prices come from the OpenRouter catalogue and re-observe on every refresh. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply $2.50 total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.

What is the context window of Gemini 3 Flash Preview?

Gemini 3 Flash Preview has a published context window of 1M tokens (1,048,576). The snapshot lists a 65,536 token catalogue-declared route output cap. OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. The providers table lists each endpoint's context limit.

Is Gemini 3 Flash Preview open-weight?

No linked weights. No downloadable model weights are linked in the current source data. This does not identify every API or chat product that offers the model.

Which API providers serve Gemini 3 Flash Preview?

2 providers serve Gemini 3 Flash Preview through OpenRouter as of 6 November 2026: Google and Google AI Studio. Each provider's price, context limit, quantization and measured uptime are in the providers table above.

Which benchmarks has Gemini 3 Flash Preview been evaluated on?

Gemini 3 Flash Preview has published results on 4 public boards tracked by ModelCap as of 6 November 2026: Arena text 1473 (#45 of 419), Arena coding 1505 (#68 of 414), ARC-AGI-2 33.6% (#124 of 280) and SWE-bench 75.8% (#2 of 47). Each board page ranks every tracked model on that benchmark. The ModelCap Index scores the results its methodology admits, with published uncertainty, and shows reference boards without scoring them.

When was Gemini 3 Flash Preview released?

Gemini 3 Flash Preview first appeared in the catalogue on 17 Dec 2025. It has since been superseded by Gemini 3.8 Flash. Rank and price movements since then are recorded on the site's changes feed.