Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. All models overview
  2. Text
  3. Google

Gemini 4 Argon

Google's Gemini 4 Argon is a flagship reasoning model for complex software engineering, mathematical and scientific problem solving, and multi-step agents. It accepts text, images, audio, video, and PDFs, with tool calling and structured outputs. Its 1,048,576-token context is shared across input, thinking, and output; synchronous output is capped at 65,536 tokens.

  • Reasoning
  • Vision
  • Audio Input
  • Video Input
  • Native PDF input
  • Tool Calling
  • Structured Output

Added Oct 13, 2026

Pricing

Auto routing · per 1M tokens
Input
$2.00
Output
$10.00
Cache read
$0.10
Compare provider prices

Specifications

Context window
1M
Max output
65.5K

Benchmarks

Sourced from LMArena.

Arena Score

1519.6

Overall Rank

#2 / 426

Votes

27,193

Confidence Interval

1514.6 - 1524.7

Category Scores

Coding

#3 / 421

6,297 votes

1552.4

Math

#1 / 408

1,407 votes

1535.3

Longer Query

#1 / 404

11,958 votes

1540.1

Creative Writing

#2 / 424

6,397 votes

1519.9

Instruction Following

#1 / 426

9,804 votes

1526.3

Hard Prompts

#2 / 426

17,294 votes

1544.3

Additional Categories
22

German

#1 / 321

390 votes

1574.8

Industry Business And Management And Financial Operations

#1 / 419

4,605 votes

1513.8

Industry Entertainment And Sports And Media

#1 / 424

7,300 votes

1513.3

Industry Legal And Government

#1 / 397

2,176 votes

1527.0

Industry Life And Physical And Social Science

#1 / 424

4,376 votes

1539.6

Industry Medicine And Healthcare

#1 / 394

1,824 votes

1533.7

Spanish

#1 / 307

1,049 votes

1506.2

English

#2 / 426

10,007 votes

1522.7

Exclude Ties

#2 / 426

20,638 votes

1544.1

Hard Prompts English

#2 / 424

6,445 votes

1541.9

Industry Mathematical

#2 / 405

1,544 votes

1542.2

Industry Software And It Services

#2 / 426

9,439 votes

1547.2

Industry Writing And Literature And Language

#2 / 425

8,199 votes

1520.6

Multi Turn

#2 / 424

3,835 votes

1541.5

Polish

#2 / 243

396 votes

1533.2

Chinese

#3 / 399

2,242 votes

1586.1

French

#3 / 305

1,020 votes

1548.2

Japanese

#3 / 288

391 votes

1522.3

Korean

#3 / 289

321 votes

1487.4

Non English

#3 / 426

17,178 votes

1510.3

Russian

#3 / 390

4,166 votes

1530.7

Expert

#4 / 374

2,649 votes

1548.5

Published 2026-11-19 · Matched as Gemini 4 Argon (High) · CC BY 4.0

LMArena Dataset

Leaderboard results

BenchmarkScoreRank on NanoGPT
Epoch AI Benchmarking Hub

Epoch AI data, CC BY 4.0 · Updated Nov 22, 2026

Epoch Capabilities Index

166.5

#11 of 114

FrontierMath v2 (Tiers 1–3)

86.0%

#15 of 84

GPQA Diamond

96.4%

#4 of 119

SimpleQA Verified

76.0%

#4 of 84

FrontierMath v2 (Tier 4)

78.0%

#15 of 68

OTIS Mock AIME 2024–2025

100.0%

#5 of 121

MirrorCode

58.9%

#14 of 41

Chess Puzzles

59.0%

#12 of 83

Mystery Game Puzzles

64.0%

#11 of 80

EQ-Bench

EQ-Bench data, MIT · Updated Nov 22, 2026

EQ-Bench 4

1236

#12 of 31

Creative Writing v3

1758

#29 of 91

Longform Writing

80.9

#14 of 93

UGI Leaderboard

UGI Leaderboard data, Apache-2.0 · Updated Nov 22, 2026

UGI Score

49.9

#39 of 125

UGI Willingness

1.8

#111 of 125

UGI Writing

79.7

#1 of 125

Filtered and ranked to models on NanoGPT.

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Cache write /M
Auto
Auto
Recommended
$2.00$10.00$0.10$0.188N/AN/A
Google Vertex
Google Vertex
US
$2.10$10.50$0.105$0.197N/AN/A
Privacy:No training on prompts

Related text models

Compare Gemini 4 Argon with similar models from the same provider or model family.

Gemini 4 Neon

google/gemini-4-neon

Google's Gemini 4 Neon is a reasoning model for complex coding, document analysis, scientific problem solving, and multi-step tasks that use tools. It accepts text and images and produces text, with tool calling and structured outputs. Its 1,048,576-token context is shared across input, thinking, and output, with up to 983,040 input tokens and 65,536 combined thinking and output tokens per response. Choose low, medium, high, or extra-high thinking; high is the default.

Gemini 4 Hydrogen

google/gemini-4-hydrogen

Google's Gemini 4 Hydrogen is a reasoning model for coding, problem solving, and multi-step tasks that use tools. It accepts text, images, audio, video, and PDFs and produces text, with tool calling and structured outputs. Its 1,048,576-token context is shared across input, thinking, and output, with up to 65,536 combined thinking and output tokens per response. Choose low, medium, high, or extra-high thinking; high is the default.

Gemini 4 Carbon

google/gemini-4-carbon

Google's Gemini 4 Carbon is a reasoning model for complex coding, scientific and mathematical problem solving, and multi-step tasks that use tools. It accepts text, images, audio, video, and PDFs and produces text, with tool calling and structured outputs. Its 1,048,576-token context is shared across input, thinking, and output. Responses support up to 32,768 combined thinking and output tokens, with low, medium, and high thinking levels; medium is the default.

Gemini 3.8 Flash

google/gemini-3.8-flash

Google's fast multimodal model for agentic workloads, including coding, tool use, image understanding, PDF and document extraction, audio, and video. Its capabilities, limits, reasoning behavior, and pricing currently mirror Gemini 3.7 Flash.

Gemini 3.7 Flash

google/gemini-3.7-flash

Google's frontier-performance Flash model for multimodal and agentic workloads, including coding, tool use, image understanding, PDF and document extraction, audio, and video. Google reports 65.3% on DeepSWE v1.1, up from 49.0% for Gemini 3.6 Flash, and 34% on GDP.pdf, up from 14%.

Gemini 3.5 Flash Lite

google/gemini-3.5-flash-lite

Google's cost-efficient Gemini 3.5 Flash Lite model for high-volume multimodal reasoning, tool use, and structured-output workloads.