Skip to content
ModelCap

Gemini 3.7 Flash

Arena #17No linked weights

Google·#21 of 533 in the all-versions archive

Gemini 3.7 Flash is a language model from Google. It ranks #21 of 533 in ModelCap's all-versions archive, with an Index score of 79.6, measured on 4 public benchmarks. Its score range of 75.0–84.2 spans positions #6–#58. It is listed at $0.75 per million input tokens and $3.75 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 19 Nov 2026, 05:16 UTC · download the public dataset · methodology

ModelCap Index · All-versions archive
79.6#21
Measured on 4 public benchmarks · range 75.0–84.2
Evidence as of 18 Nov 2026, 14:36 UTC
Market Gravity
52.1Increased by 0.8
Secondary market signal

Superseded by Gemini 3.8 Flash. It no longer holds a current-board position; its all-versions archive rank is #21.

Input
$0.75
per 1M tokens
Output
$3.75
per 1M tokens
Context
1M
tokens
Providers
2
6 endpoints

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Googleglobal/flexCheapest$0.375$1.881M—60.00%
Google AI Studioflex$0.375$1.881M—100.0%
Googleglobal$0.75$3.751M—100.0%
Google AI Studio$0.75$3.751M—100.0%
Googleglobal/priority$1.35$6.751M—100.0%
Google AI Studiopriority$1.35$6.751M——

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
High
Gemini 3.7 Flash (High)
-3.07%
CI -4.0–-2.1%
#466.2M obs
63K sessions
LMArena Agent
Match 100%

Related community configurations

Human preference rating
ConfigurationRatingSource rankVotesSource
High
Gemini 3.7 Flash (High)
1490
CI 1485–1494
#1733KLMArena
Match 100%

Publisher launch results (8)

Publisher’s own claims

Scores Google publishes for this model, with the figures the same tables give for other models. They are the publisher describing its own model, not independent measurement. An independent general board already measures this model, so these claims play no part in its score.

BenchmarkReportedSame table, other models
Artificial Analysis Intelligence Index
56
GPT-5.6 Terra 57 · Muse Spark 1.2 57 · Claude Sonnet 5 55 · Gemini 3.6 Flash 52
FrontierCode 1.1 main score
43.6
Claude Sonnet 5 42.7 · GPT-5.6 Terra 41.3 · Gemini 3.6 Flash 34.4
DeepSWE v1.1
65.3
GPT-5.6 Terra 69.6 · Muse Spark 1.2 54.9 · Claude Sonnet 5 53.8 · Gemini 3.6 Flash 48.6
Terminal-Bench 2.1
85.8
GPT-5.6 Terra 87.4 · Muse Spark 1.2 82.9 · Claude Sonnet 5 80.4 · Gemini 3.6 Flash 78
Terminal-Bench 3.0
14.9
GPT-5.6 Terra 20.8 · Claude Sonnet 5 14.6 · Gemini 3.6 Flash 5.4
AutomationBench private set
30.4
GPT-5.6 Terra 23.6 · Gemini 3.6 Flash 17 · Claude Sonnet 5 10.7
OSWorld 2.0
47.9
GPT-5.6 Terra 50.2 · Gemini 3.6 Flash 33.8
Humanity’s Last Exam Verified
53.6
Gemini 3.6 Flash 51.2 · GPT-5.6 Terra 51.1 · Claude Sonnet 5 31

Other versions (5)

ModelCap Index · All-versions archive

Methodology
79.6
Measured on 4 public benchmarks
All-versions archive
#21 of 533
Score range
75.0–84.2
Rank range
#6–#58
Evidence as of
18 Nov 2026, 14:36 UTC
Benchmarks used
ARC-AGI-2 Verified, Arena Coding, Arena Overall, LMArena Agent
Technical details
Public rank basis
Measured (measured)
Evidence label
Measured · 4 public benchmark observations across 4 boards
Index support
67.9% · strong
Identity binding
Exact catalogue product · google/google/gemini-3.7-flash · aggregates disclosed benchmark configurations · endpoint configuration not claimed
Index observations used
4
Qualified Index evidence point
79.6
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
79.6
Evidence status
confirmed · 90% mass
General preference
81.7
Coding
76.7
Agents & tools
37.5
Reasoning
72.8
Evidence breadth
100%
Evidence coverage
68%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
31.4
Liquidity (providers × uptime)
95.5
Open reach (HF downloads)
—
Surface (context / tools / modalities)
100.0
Freshness
69.0
  • · OpenRouter popularity #55
  • · 2 live providers
  • · Catalogue: context 1048576, reasoning, tools, modalities Text/Image/Video/File/Audio
  • · First seen 2026-08-13

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
49.8
partial · 56% metadata coverage
Not capability
Artifact reproducibility
0.0
Access & legal clarity
30.3
Deployability
86.0
Evaluation provenance
89.7

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
52.1
OpenRouter weekly popularity
#55 of 345

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
#17 of 422
Rating
1489.7
95% confidence interval
1485–1494
Votes
33K
Source published at
18 Nov 2026, 00:00 UTC
Category
overall
Identity match confidence
100%

Market Gravity breakdown

Usage55%
31.4

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
95.5

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%
69.0

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

Specification

Model ID
google/gemini-3.7-flash
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, Video, File, Audio
Outputs
Text
Tokenizer
Gemini
Cached input tokens
$0.075 / 1M
First seen on OpenRouter
13 Aug 2026

Capabilities

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

Benchmark leaderboards featuring Gemini 3.7 Flash

All leaderboards
Public benchmark boards on which Gemini 3.7 Flash has a published result
LeaderboardScoreSource rankConfigurationPublished
Arena text leaderboardArena (LMArena)14901485–1494#17 of 422High18 Nov 2026
Arena coding leaderboardArena (LMArena)15211513–1528#35 of 417High18 Nov 2026
LMArena Agent leaderboardLMArena-3.1%-4.0%–-2.1%#46 of 68High18 Nov 2026
ARC-AGI-2 leaderboardARC Prize Foundation84.6%#46 of 299High18 Nov 2026
Terminal-Bench 4.0 leaderboardTerminal-Bench (Laude Institute)11.2%8.8%–13.7%#35 of 35mini-SWE-agent · High13 Aug 2026

Gemini 3.7 Flash: common questions

How does Gemini 3.7 Flash rank among AI models?

Gemini 3.7 Flash is a superseded version and is not on the current board as of 19 November 2026. Its archive position, where one exists, is shown on the page; the newer version carries the current rank.

How much does Gemini 3.7 Flash cost per 1M tokens?

Gemini 3.7 Flash is listed at $0.75 per 1M input tokens and $3.75 per 1M output tokens as of 19 November 2026; the lowest output price among 2 providers is $1.88 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 $3.38 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 3.7 Flash?

Gemini 3.7 Flash 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 3.7 Flash 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 3.7 Flash?

2 providers serve Gemini 3.7 Flash through OpenRouter as of 19 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 3.7 Flash been evaluated on?

Gemini 3.7 Flash has published results on 5 public boards tracked by ModelCap as of 19 November 2026: Arena text 1490 (#17 of 422), Arena coding 1521 (#35 of 417), LMArena Agent -3.1% (#46 of 68), ARC-AGI-2 84.6% (#46 of 299) and Terminal-Bench 4.0 11.2% (#35 of 35). 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 3.7 Flash released?

Gemini 3.7 Flash first appeared in the catalogue on 13 Aug 2026. It has since been superseded by Gemini 3.8 Flash. Rank and price movements since then are recorded on the site's changes feed.