NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Gemini 3.8 Flash
Google DeepMind logo

Gemini 3.8 Flash

by Google DeepMind · Released Sep 2026

Multimodal1M Context
66.3
avg score
Rank #52
Compare
Better than 84% of all models
Context
1.0M tokens (~524 books)
Input $/1M
$0.82
Output $/1M
$4.13
Type
multimodal
License
Proprietary
Benchmarks
30 tested
Data as of
About

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Tested on 30 benchmarks · BenchGecko score 66.3. Top scores: OTIS Mock AIME 2024-2025 (98.9%), ARC-AGI (98.5%), GPQA diamond (97.8%).

Looking for similar performance at lower cost?
Kimi K3 scores 65.8 (99% as good) at $0.24/1M input · 71% cheaper
Capabilities
coding
54.9
#73 globally
reasoning
93.8
#6 globally
math
64.3
#75 globally
knowledge
56.2
#88 globally
agentic
64.3
#11 globally
general
47.1
#42 globally
speed
59.1
#10 globally
Benchmark Scores
Compare All
Tested on 30 benchmarks · Ranked across 7 categories
Score Distribution (all 320 models)
0255075100
▲ You are here
codingCompare coding →
WeirdML

Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.

84.8·
Deepswe
73.8·
Frontiercode
41.2·
reasoningCompare reasoning →
ARC-AGI

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

98.5·
ARC-AGI-2

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

89.2·
mathCompare math →
OTIS Mock AIME 2024-2025

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

98.9·
FrontierMath-Tiers-1-3-v2-Private
72.0·
FrontierMath-Tier-4-v2-Private
21.9·
Quick compare:DeepSeek logovs DeepSeek V4 Pro 0813moonshotai logovs Kimi K3Google DeepMind logovs Gemini 3.7 Flash
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · Google DeepMind Gemini 3.8 Flash
Sep 2026
66.3
$0.82/M in1.0Mctx29 benchmarks
Sep 2026
$0.38/M in(-0.45)1.0Mctx
See the full Gemini 3.8 Flash family →
Recently Happened
Gemini 3.8 Flash pricing increased 10%
Oct 16, 2026
Gemini 3.8 Flash added
Sep 3, 2026
Similar Models
DeepSeek logo
DeepSeek V4 Pro 0813
DeepSeek
66.0$0.66/1M
moonshotai logo
Kimi K3
moonshotai
65.8$0.24/1M
Google DeepMind logo
Gemini 3.7 Flash
Google DeepMind
67.1$0.75/1M
Links
Info
Google DeepMindPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Google DeepMind
BenchGecko API
gemini-3-8-flash
Specifications
  • Typemultimodal
  • Context1.0M tokens (~524 books)
  • ReleasedSep 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.006
Available On
Google DeepMind logoGoogle DeepMind$0.82
Categories
codingreasoningmathknowledgeagenticgeneralspeed
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
DeepSeek logoDeepSeek V4 Pro 0813
66.0
moonshotai logoKimi K3
65.8
Google DeepMind logoGemini 3.7 Flash
67.1
Anthropic logoClaude Opus 4.6
65.2
Gemini 3.8 Flash is a proprietary multimodal AI model by Google DeepMind, released in September 2026. It has an average benchmark score of 66.3. Context window: 1M tokens.

Related Models

DeepSeek V4 Pro 0813 · DeepSeekKimi K3 · moonshotaiGemini 3.7 Flash · Google DeepMindClaude Opus 4.6 · AnthropicGrok 4.6 · xAI

Benchmarks

OTIS Mock AIME 2024-2025ARC-AGIGPQA diamondArtificial Analysis · GPQA DiamondDtbench

Related Pages

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

Key facts · as of 2026-10-25

  • Gemini 3.8 Flash by Google DeepMind. BenchGecko score 66.3, rank 52 of 320 scored models (normalized average of public benchmark scores).
  • List price $0.82 input · $4.13 output per 1M tokens (as of 2026-10-25).
  • Sold by 7 providers (as of 2026-10-25): 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 $0.82 in / $4.13 out · and 2 more. Every provider
  • Gecko Tests · Gecko Score 57 (rank 16): Who Are You B (Knows who made it) · World Map A (97.4% of the map right) · Knowledge Horizon E (Knows news up to Mar 2025) · Tokenizer Tax B (44% more tokens outside English).

How to cite · data as of 2026-10-25

Gemini 3.8 Flash · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-25. https://benchgecko.ai/model/gemini-3-8-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