Skip to content
ModelCap

Gemini 3 Flash Preview

All-versions archive #23Arena #27API only

Google·google/gemini-3-flash-preview

Gemini 3 Flash Preview is a language model published by Google. 6 OpenRouter endpoints are published in the latest snapshot. It accepts text, image, file, audio, video input and returns text. The published context limit is 1.0M tokens. The catalogue declares support for reasoning, tool use, structured outputs.

ModelCap Index · All-versions archive
82.8#23
Measured · 92% support · score interval 82.8–88.0
Market Gravity
56.7
Secondary market signal

Superseded by Gemini 3.6 Flash. It no longer holds a current-board position; its all-versions archive rank is #23.

Input
$0.50
per 1M tokens
Output
$3.00
per 1M tokens
Context
1.0M
tokens
Providers
6
endpoints
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Google AI StudioflexCheapest$0.25$1.501.0M—99.83%
Googleglobal/flex$0.25$1.501.0M—96.97%
Google AI Studio$0.50$3.001.0M—99.83%
Googleglobal$0.50$3.001.0M—96.97%
Google AI Studiopriority$0.90$5.401.0M—99.83%
Googleglobal/priority$0.90$5.401.0M—96.97%

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.

EffortAgent scoreSource rankSampleSource
Default
Gemini 3 Flash
-8.83%
CI -9.6–-8.1%
#401.7M obs
79K sessions
LMArena Agent
Match 98%

Related community configurations

Human preference rating
ConfigurationRatingSource rankVotesSource
Thinking · Minimal
gemini-3-flash (thinking-minimal)
1459
CI 1455–1462
#4886KArena
Match 98%

Other versions (3)

ModelCap Index · All-versions archive

Methodology
82.8
Measured · 5 public benchmark observations across 5 boards
All-versions archive
#23
Public rank basis
Measured (measured)
Index support
92.0% · strong
Index interval
82.8–88.0
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · google/google/gemini-3-flash-preview · aggregates disclosed benchmark configurations · endpoint configuration not claimed
Direct benchmark observations
5
Breadth-adjusted BES point estimate
85.4
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
85.4
Evidence status
confirmed · 98% mass
General preference
89.8
Coding
90.1
Agents & tools
18.0
Reasoning
60.0
Evidence breadth
100%
Evidence coverage
92%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
51.3
Liquidity (providers × uptime)
75.7
Open reach (HF downloads)
—
Surface (context / tools / modalities)
100.0
Freshness
41.1
  • · OpenRouter popularity #16
  • · 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
50.6
partial · 56% metadata coverage
Not capability
Artifact reproducibility
0.0
Access & legal clarity
30.3
Deployability
89.7
Evaluation provenance
88.1

Missing: artifactReproducibility.revision-sha, artifactReproducibility.architecture-and-model-type, artifactReproducibility.parameter-count, artifactReproducibility.serialized-weight-format, artifactReproducibility.base-lineage, accessLegalClarity.declared-license, accessLegalClarity.resolvable-license-terms, evaluationProvenance.evaluation-dataset-revisions.

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

Market activity

Venue coverage
Market Gravity
56.7
OpenRouter weekly popularity
#16 of 298

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
Arena
Official rank
#27 of 385
Rating
1472.8
95% confidence interval
1468–1477
Votes
31K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
98%

Market Gravity breakdown

Usage55%
51.3

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
75.7

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%
41.1

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

Specification

Context window
1.0M tokens
Max output
66K tokens
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