Skip to content

Google · Chat

Gemini 3.7 Flash

Google 🇺🇸ChatGemini familyOne of its sources says the weights aren't publicly available.The maker currently plans to deprecate it within the next 180 days (28 Jan 2027). Plans can change.

Newer version: Gemini 3.8 Flash. We compared release dates and version names in our catalogue.

From Neosantara's listing:
The next iteration in the Gemini 3 model family, featuring algorithmic improvements to its core reasoning foundation and customizable thinking configurations to control the mix of quality, cost, and latency.
llminfo IQ
138.8
Maker's price
$1.50 blended / 1M
Max context
1M
Listings
64

Evidence and sources

llminfo IQ 138.8, ranked among chat models. From 267 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 121.3, 95% interval 113–130. From 20 benchmark families across 9 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedGood value (60.3). Cheaper per task than its benchmark results predict. From 44 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsChatty (59 ±12). Generates more tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it. By effort: default 51 · low 55 · medium 59 · high 59.Median 107,248 output tokens per task at high effort.How the Yap score worksReleased 13 Aug 2026Maker HQ: US (according to Google's own website)
All rankings: #55 on OpenRouter this month #64 on OpenRouter today #64 on OpenRouter this week #179 on NanoGPT recentlySources: Google Generative AI API data docs, Writer Pricing, ModelRunner.ai data, LiteLLM data, AI/ML API data, Neosantara Inference data, llminfo researchPrimary data from Google Generative AI API from Writer Pricing: variant from ModelRunner.ai: weights availability from LiteLLM: deprecation date from AI/ML API: primary mode from Neosantara Inference: description from llminfo research: release date
Tags from its sources:instructtoolsvisionreasoningaudiodocument

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Trade-offs

Deprecation scheduled

The maker plans to deprecate it on 28 Jan 2027, within the next 180 days.

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Images
Audio
Video
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingPDF inputComputer useWeb searchAudio inputBatch API

Listings

 Googlemodels/gemini-3.7-flashSources: Google Generative AI API data docs, Google Vertex AI Pricing, LiteLLM data, Models.dev data1M$0.75>200k $0.75cache read $0.075batch $0.375$3.75>200k $3.75batch $1.875———
 Kenarigemini-3-7-flashSource: Models.dev data1M$0.3429cache read $0.0343$1.71———
 Nous Portalgoogle/gemini-3.7-flash:batch · batchSource: Nous Portal Inference Gateway data1M$0.375cache read $0.0375$1.875$0.375—$0.00000038
 OpenRouterInference by Googlegoogle/gemini-3.7-flash:batch · batch, globalSource: OpenRouter data docs1M$0.375cache read $0.0375$1.875$0.375$0.0375$0.00000038
 Meganovagemini/gemini-3.7-flashSource: MegaNova data1M$0.60$3.00———
 Cortecs AIgemini-3.7-flashSources: Cortecs EU Router data, Models.dev data1M———
 Databricksdatabricks/databricks-gemini-3-7-flashSource: LiteLLM data1M$0.75cache read $0.075$3.75cache write $0.75———
 302aigemini-3.7-flashSource: Models.dev data1M$0.75cache read $0.075$3.75———
 Aihubmixgemini-3.7-flashSources: AIHubMix data docs, LiteLLM data1M$0.75cache read $0.075$3.75———
 Cometapigemini-3.7-flashSources: CometAPI data, CometAPI Pricing dataNot published by the provider$0.75$3.75———

12 listings without a price are hidden.

Included in plans

Copilot EnterprisegithubSubscription$39/moextra use billed past the allowancePlan page
Copilot ProgithubSubscription$10/moextra use billed past the allowancePlan page
Copilot Pro+githubSubscription$39/moextra use billed past the allowancePlan page
Copilot BusinessgithubSubscription$19/moextra use billed past the allowancePlan page
Copilot MaxgithubSubscription$100/moextra use billed past the allowancePlan page

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Arena ELO58 related benchmarks · 58 results
Source: LMArena data · Nov 2026
BenchmarkHigh
Arena ELO
Chinese
Creative Writing
Document
Show 54 more benchmarksHide 54 benchmarks
BenchmarkHigh
Document Style-Controlled
English
Exclude Ties
Expert
French
German
Hard Prompts
Hard Prompts English
Industry Business and Management and Financial Operations
Industry Entertainment and Sports and Media
Industry Life and Physical and Social Science
Industry Mathematical
Industry Medicine and Healthcare
Industry Software and It Services
Industry Writing and Literature and Language
Japanese
Korean
Longer Query
Multi Turn
Non English
Polish
Russian
Spanish
Style-Controlled
Text Factuality
Text Factuality - Chinese
Text Factuality - Creative Writing
Text Factuality - English
Text Factuality - Exclude Ties
Text Factuality - Expert
Text Factuality - Hard Prompts
Text Factuality - Hard Prompts English
Text Factuality - Industry Business and Management and Financial Operations
Text Factuality - Industry Entertainment and Sports and Media
Text Factuality - Industry Life and Physical and Social Science
Text Factuality - Industry Mathematical
Text Factuality - Industry Medicine and Healthcare
Text Factuality - Industry Software and It Services
Text Factuality - Industry Writing and Literature and Language
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Russian
Text Factuality - Spanish
Vision
Vision - Chinese
Vision - Creative Writing Vision
Vision - Diagram
Vision - English
Vision - Homework
Vision - Humor
Vision Style-Controlled
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Agentic

Arena AgentSource: LMArena data
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026
GDPval-AASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GDPval-AA v22 results
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Setting not stated
Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Artificial Analysis / Z.ai转载
Harvey LAB-AA2 results
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
official model-card metric
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Terminal-Bench 2.14 related benchmarks · 6 results
Terminal-Bench 2.1
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Terminal-Bench 3.0
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
mini-swe-agent · highest thinking
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Terminal-Bench 4.0
Reported by Terminal-Bench / Stanford / Harbor / Laude Institute · via BenchBoard docs
Terminal-Bench 4.0 official leaderboard · mini-SWE-agent · high effort

Coding

Arena ELOSource: LMArena data · Nov 2026
ValsSource: Vals AI

General

Long context

Reasoning

Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
v1.0.6 / Z.ai Flash表
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Human Difficult subset
Human Solvable subset
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
GDP.pdf2 results
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Speech

Multilingual

EKI EstonianSource: Keelemudelite mõõdupuu data docs · Aug 2026

Science

GPQA Diamond4 results
Source: OpenRouter benchmark exports · Oct 2026
13 Aug 2026 version · 90-day results
Across 2 providers lowest 94.1% median 94.3% highest 94.5%OpenRouter's automatic routing 93.9%
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
  • Google
  • Google AI Studio
  • OpenRouter's automatic routing
LABBench22 results
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Vision

CharXiv-RSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
LVBench2 results
Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
no tools · 1,024 frames
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Math

Instruction following

Factuality

Knowledge

OCR

Other

DeepSWE v1.1mini-swe-agent · LiteLLM 1.96 · high thinking · Reported by Google DeepMind · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
RecreationBench paper25 related benchmarks · 25 results
Web · Visual assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Web · nominal 50-task split · platform-specific score
Android · Applications with Prog =100%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Android · nominal 50-task split · platform-specific score
Android · Applications with Prog ≥90%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Android · nominal 50-task split · platform-specific score
Android · Programmatic assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Android · nominal 50-task split · platform-specific score
Android · Visual assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Android · nominal 50-task split · platform-specific score
macOS · Applications with Prog =100%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · macOS · nominal 50-task split · platform-specific score
Show 19 more resultsHide 19 results
macOS · Applications with Prog ≥90%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · macOS · nominal 50-task split · platform-specific score
macOS · Programmatic assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · macOS · nominal 50-task split · platform-specific score
macOS · Visual assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · macOS · nominal 50-task split · platform-specific score
Overall · Applications with Prog =100%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Overall · 250 held-out tasks · equal-weight platform macro average
Overall · Applications with Prog ≥90%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Overall · 250 held-out tasks · equal-weight platform macro average
Overall · Programmatic + visual mean
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Overall · 250 held-out tasks · equal-weight platform macro average
Overall · Programmatic assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Overall · 250 held-out tasks · equal-weight platform macro average
Overall · Visual assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Overall · 250 held-out tasks · equal-weight platform macro average
Ubuntu · Applications with Prog =100%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Ubuntu · nominal 50-task split · platform-specific score
Ubuntu · Applications with Prog ≥90%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Ubuntu · nominal 50-task split · platform-specific score
Ubuntu · Programmatic assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Ubuntu · nominal 50-task split · platform-specific score
Ubuntu · Visual assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Ubuntu · nominal 50-task split · platform-specific score
Web · Applications with Prog =100%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Web · nominal 50-task split · platform-specific score
Web · Applications with Prog ≥90%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Web · nominal 50-task split · platform-specific score
Web · Programmatic assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Web · nominal 50-task split · platform-specific score
Windows · Applications with Prog =100%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Windows · nominal 50-task split · platform-specific score
Windows · Applications with Prog ≥90%
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Windows · nominal 50-task split · platform-specific score
Windows · Programmatic assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Windows · nominal 50-task split · platform-specific score
Windows · Visual assertion score
Reported by QwenLM / RecreationWorld authors · via BenchBoard docs
RecreationWorld benchmark-owner paper run · 250 held-out tasks · GUI exploration + coding tools + visual verification · high reasoning effort per site data · 1m context · 64k max output tokens · Windows · nominal 50-task split · platform-specific score
SkillsBench · Vals6 related benchmarks · 6 results
With Skills · Accuracy
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=google/gemini-3.7-flash · provider=Google · reasoning_effort=high · temperature=1 · max_output_tokens=65536
With Skills · Mean cost / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=google/gemini-3.7-flash · provider=Google · reasoning_effort=high · temperature=1 · max_output_tokens=65536
With Skills · Mean duration / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=google/gemini-3.7-flash · provider=Google · reasoning_effort=high · temperature=1 · max_output_tokens=65536
Without Skills · Accuracy
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=google/gemini-3.7-flash · provider=Google · reasoning_effort=high · temperature=1 · max_output_tokens=65536
Without Skills · Mean cost / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=google/gemini-3.7-flash · provider=Google · reasoning_effort=high · temperature=1 · max_output_tokens=65536
Without Skills · Mean duration / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=google/gemini-3.7-flash · provider=Google · reasoning_effort=high · temperature=1 · max_output_tokens=65536
Vals9 related benchmarks · 11 results
EMB
Source: Vals AI
LegalBench
Source: Vals AI
MedCode
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
MedScribe
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
Show 3 more resultsHide 3 results
MortgageTax
Source: Vals AI
SRE Bench
Source: Vals AI
TaxEval v2
Source: Vals AI

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · BullshitBench by Peter Gostev, MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Deep20Bench edition 1.1, Patrick Heusser. Results CC BY 4.0; native question scores and fraction-to-percent success rates. (licence) · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MineBench, MIT (licence) · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted. · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence)

Around the web

Also known as: aihubmix/gemini-3.7-flash, databricks/databricks-gemini-3-7-flash, deepinfra/google/gemini-3.7-flash, gemini 3.7 flash, gemini-3-7-flash, gemini-3.7-flash-high, gemini-3.7-flash-thinking, gemini-3.7-flash@eu, gemini/gemini-3.7-flash, github_copilot/gemini-3.7-flash, gmi/google/gemini-3.7-flash, google-gemini-3.7-flash, google-vertex/gemini-3.7-flash, google/gemini-3-7-flash, google/gemini-3.7-flash, google/gemini-3.7-flash:batch, modelrunner-ai/google-gemini-3.7-flash, perplexity/google/gemini-3.7-flash, vertex/gemini-3.7-flash, vertex/gemini-3.7-flash@eu, vertex/gemini-3.7-flash@us, vertex_ai/gemini-3.7-flash

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works