66.4
avg score
Rank #51
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 updated today
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 with 57.6% average. 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 $0.66/1M input · 12% cheaper
DeepSeek V4 Pro 0813 scores 66.8 (101% as good) at $0.66/1M input · 12% 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 AllTested on 18 benchmarks · Ranked across 6 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
reasoningCompare reasoning →
ARC-AGI
95.5—Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.
ARC-AGI-2
84.6—ARC-AGI 2, harder sequel to ARC. More complex abstract reasoning patterns that test generalization ability beyond training data.
mathCompare math →
OTIS Mock AIME 2024-2025
97.2—Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Recently Happened
Gemini 3.7 Flash pricing increased 100%
Aug 29, 2026
Gemini 3.7 Flash added
Aug 14, 2026
Links
Research
Documentation
Community
BenchGecko API
gemini-3-7-flash
Specifications
- Typemultimodal
- Context1.0M tokens (~524 books)
- ReleasedAug 2026
- LicenseProprietary
- StatusActive
- Cost / Message~$0.005
Available On
Learn More
Share & Export
Frequently Asked Questions
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.