NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Gemini 3.7 Flash
Google DeepMind logo

Gemini 3.7 Flash

by Google DeepMind · Released Aug 2026

Multimodal1M Context
66.4
avg score
Rank #51
Compare
Better than 84% of all models
Context
1.0M tokens (~524 books)
Input $/1M
$0.75
Output $/1M
$3.75
Type
multimodal
License
Proprietary
Benchmarks
18 tested
Data as of
About

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...

Tested on 18 benchmarks · BenchGecko score 66.4. Top scores: OTIS Mock AIME 2024-2025 (97.2%), ARC-AGI (95.5%), Dtbench (94.7%).

Looking for similar performance at lower cost?
DeepSeek V4 Pro 0813 scores 66.8 (101% as good) at $0.55/1M input · 27% cheaper
Capabilities
coding
43.1
#127 globally
reasoning
90.0
#5 globally
math
68.5
#54 globally
knowledge
68.8
#23 globally
agentic
67.8
#6 globally
general
41.3
#64 globally
Benchmark Scores
Compare All
Tested on 18 benchmarks · Ranked across 6 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
Deepswe
65.5·
Frontiercode
43.6·
Frontierswe
20.3·
reasoningCompare reasoning →
ARC-AGI

Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.

95.5·
ARC-AGI-2

ARC-AGI 2, harder sequel to ARC. More complex abstract reasoning patterns that test generalization ability beyond training data.

84.6·
mathCompare math →
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

97.2·
FrontierMath-Tiers-1-3-v2-Private
71.6·
FrontierMath-Tier-4-v2-Private
36.6·
Quick compare:Anthropic logovs Claude Opus 4.6Anthropic logovs Claude Sonnet 5xAI logovs Grok 4.6
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · Google DeepMind Gemini 3.7 Flash
Aug 2026
66.4
$0.75/M in1.0Mctx18 benchmarks
Aug 2026
$0.38/M in(-0.38)1.0Mctx
See the full Gemini 3.7 Flash family →
Recently Happened
Gemini 3.7 Flash pricing increased 100%
Aug 29, 2026
Gemini 3.7 Flash added
Aug 14, 2026
Similar Models
Anthropic logo
Claude Opus 4.6
Anthropic
66.4$5.00/1M
Anthropic logo
Claude Sonnet 5
Anthropic
66.3$2.00/1M
xAI logo
Grok 4.6
xAI
66.2$2.00/1M
Links
Info
Google DeepMindPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Google DeepMind
BenchGecko API
gemini-3-7-flash
Specifications
  • Typemultimodal
  • Context1.0M tokens (~524 books)
  • ReleasedAug 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.005
Available On
Google DeepMind logoGoogle DeepMind$0.75
Categories
codingreasoningmathknowledgeagenticgeneral
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
Anthropic logoClaude Opus 4.6
66.4
Anthropic logoClaude Sonnet 5
66.3
xAI logoGrok 4.6
66.2
DeepSeek logoDeepSeek V4 Pro 0813
66.8
Gemini 3.7 Flash is a proprietary multimodal AI model by Google DeepMind, released in August 2026. It has an average benchmark score of 66.4. Context window: 1M tokens.

Related Models

Claude Opus 4.6 · AnthropicClaude Sonnet 5 · AnthropicGrok 4.6 · xAIDeepSeek V4 Pro 0813 · DeepSeekGPT-5.4 · OpenAI

Benchmarks

OTIS Mock AIME 2024-2025ARC-AGIDtbenchGPQA diamondARC-AGI-2

Related Pages

Google DeepMind · ProviderGoogle DeepMind · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-10-05

  • Gemini 3.7 Flash by Google DeepMind. BenchGecko score 66.4, rank 50 of 312 scored models (normalized average of public benchmark scores).
  • List price $0.75 input · $3.75 output per 1M tokens (as of 2026-10-05).
  • Sold by 6 providers (as of 2026-10-05): Google $0.38 in / $1.88 out · Google AI Studio $0.38 in / $1.88 out · Google $0.75 in / $3.75 out · Google AI Studio $0.75 in / $3.75 out · Google $1.35 in / $6.75 out · and 1 more. Every provider
  • Gecko Tests: Who Are You B (Knows who made it) · Tokenizer Tax B (44% more tokens outside English).

How to cite · data as of 2026-10-05

Gemini 3.7 Flash · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/gemini-3-7-flash

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP