NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Gemini 4 Argon
Google DeepMind logo

Gemini 4 Argon

by Google DeepMind · Released Oct 2026

Multimodal1M Context
88.6
avg score
Rank #9
Compare
Top 3% of all models
Context
1.0M tokens (~524 books)
Input $/1M
$2.00
Output $/1M
$10.00
Type
multimodal
License
Proprietary
Benchmarks
18 tested
Data as of
About

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

Tested on 18 benchmarks · BenchGecko score 88.6. Top scores: OTIS Mock AIME 2024-2025 (100.0%), Proofbench (99.0%), GPQA diamond (95.2%).

Looking for similar performance at lower cost?
Step 3.5 Flash scores 89.5 (101% as good) at $0.10/1M input · 95% cheaper
Capabilities
coding
51.3
#89 globally
math
88.0
#16 globally
knowledge
76.0
#7 globally
agentic
82.4
#1 globally
speed
55.7
#18 globally
general
73.4
#6 globally
Benchmark Scores
Compare All
Tested on 18 benchmarks · Ranked across 6 categories
Score Distribution (all 319 models)
0255075100
▲ You are here
codingCompare coding →
Frontierswe
55.0·
Frontiercode
47.5·
mathCompare math →
OTIS Mock AIME 2024-2025

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

100.0·
FrontierMath-Tiers-1-3-v2-Private
86.0·
FrontierMath-Tier-4-v2-Private
78.0·
knowledgeCompare knowledge →
GPQA diamond

Graduate-level science questions written by PhD experts. Diamond subset contains questions where experts disagree, testing deep understanding.

95.2·
SimpleQA Verified

Simple factual questions with verified correct answers. Tests accuracy of basic knowledge retrieval. Low scores indicate hallucination.

76.0·
Chess Puzzles

Tactical chess puzzles testing pattern recognition and multi-move calculation. Measures strategic reasoning ability.

56.9·
Quick compare:OpenAI logovs GPT-5 Chatstepfun logovs Step 3.5 Flashvs Qwen2.5 72B Instruct Abliterated
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · Google DeepMind Gemini 4
Oct 2026
88.6
$2.00/M in1.0Mctx
Oct 2026
$1.00/M in(-1)1.0Mctx
See the full Gemini 4 family →
Recently Happened
New model: Gemini 4 Argon by Google DeepMind
Oct 15, 2026
Similar Models
OpenAI logo
GPT-5 Chat
OpenAI
89.0$1.25/1M
stepfun logo
Step 3.5 Flash
stepfun
89.5$0.10/1M
Qwen2.5 72B Instruct Abliterated
HuiHui AI
87.2n/a
Links
Info
Google DeepMindPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Google DeepMind
BenchGecko API
gemini-4-argon
Specifications
  • Typemultimodal
  • Context1.0M tokens (~524 books)
  • ReleasedOct 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.014
Available On
Google DeepMind logoGoogle DeepMind$2.00
Categories
codingmathknowledgeagenticspeedgeneral
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
OpenAI logoGPT-5 Chat
89.0
stepfun logoStep 3.5 Flash
89.5
Qwen2.5 72B Instruct Abliterated
87.2
Anthropic logoClaude Opus 5
86.0
Gemini 4 Argon is a proprietary multimodal AI model by Google DeepMind, released in October 2026. It has an average benchmark score of 88.6. Context window: 1M tokens.

Related Models

GPT-5 Chat · OpenAIStep 3.5 Flash · stepfunQwen2.5 72B Instruct Abliterated · HuiHui AIClaude Opus 5 · AnthropicDeepSeek-V2 (MoE-236B, May 2024) · DeepSeek

Benchmarks

OTIS Mock AIME 2024-2025ProofbenchGPQA diamondFrontierMath-Tiers-1-3-v2-PrivateAPEX-Agents

Related Pages

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

Key facts · as of 2026-10-15

  • Gemini 4 Argon by Google DeepMind. BenchGecko score 88.6, rank 9 of 319 scored models (normalized average of public benchmark scores).
  • List price $2.00 input · $10.00 output per 1M tokens (as of 2026-10-15).
  • Sold by 6 providers (as of 2026-10-15): Google AI Studio $1.00 in / $5.00 out · Google $2.00 in / $10.00 out · Google AI Studio $2.00 in / $10.00 out · Google $2.20 in / $11.00 out · Google $3.60 in / $18.00 out · and 1 more. Every provider
  • Gecko Tests: Who Are You B (Knows who made it) · Knowledge Horizon E (Knows news up to Feb 2025).

How to cite · data as of 2026-10-15

Gemini 4 Argon · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-15. https://benchgecko.ai/model/gemini-4-argon

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