OverviewAll LeaderboardsMethodology
New Chat
Coding IndexGemini 4 Neon (High)
Google

Gemini 4 Neon (High)

Gemini 4 Neon (High) is a proprietary model from Google. It ranks #5 of 68 models on the Coding Index with 1,325. Its best signal rank is #2 of 68, on Steerability.

Coding Index Overview

Rank
#5

Rank spread 2 – 11.

Coding Index
1,325± 44
Pareto frontier
Gemini 4 Neon
Developer
Google
License
Proprietary
Reasoning effort
High
Sessions
1,625
Ranking updated
Nov 18, 2026

Cost, Time, and Tokens

Cost per task$4.76
GPT-6.1 Sol (Medium)$0.85AnthropicClaude Fable 5.2 (Max)$19.02

The median is $4.76.

Time per task13.7 min
AnthropicClaude Sonnet 5.5 (High)6.3 minAnthropicClaude Fable 5.2 (Max)39.4 min

The median is 20.8 min.

Output tokens per task102.9K
GPT-6.1 Sol (Medium)28.6KAnthropicClaude Fable 5.2 (Max)262.1K

The median is 88.9K.

Coding Ranking

1,1001,2001,3001,4001,500
  1. 1,489
    Anthropic
    Claude Fable 5.2Max#1
  2. 1,373
    Anthropic
    Claude Opus 5.5Max#2
  3. 1,338
    GPT-6.2 AstraMax#3
  4. 1,329
    Anthropic
    Claude Sonnet 5.5Max#4
  5. 1,325
    Gemini 4 NeonHigh#5
  6. 1,315
    Anthropic
    Claude Opus 5.5High#6
  7. 1,291
    Gemini 4 CarbonHigh#7
  8. 1,288
    GPT-6 AstraMax#8
  9. 1,288
    GPT-6.2 SolMax#9
  10. 1,276
    GPT-6.1 TerraMax#10
  11. 1,273
    Anthropic
    Claude Fable 5.1Max#11
  12. 1,246
    GPT-6.1 SolMax#12
  13. 1,238
    Anthropic
    Claude Sonnet 5.5High#13
  14. 1,230
    GPT-6.1 SolMedium#14
  15. 1,229
    Gemini 4 HydrogenHigh#15

Signal Performance

Gemini 4 NeonLeader
Rank on the board
  • Task CompletionHow often the model gets users to confirm the task is done.
    Claude Sonnet 5.5 (Max) · 1,373Claude Sonnet 5.5 (Max) · 1,373Gemini 4 Neon · 1,298
    #5of 68
  • Praise vs ComplaintHow often the model earns more explicitly positive responses than negative ones.
    Claude Fable 5.2 · 1,810Claude Fable 5.2 · 1,810Gemini 4 Neon · 1,478
    #4of 68
  • SteerabilityHow well the model lands user corrections when they push back.
    Claude Fable 5.2 · 1,442Claude Fable 5.2 · 1,442Gemini 4 Neon · 1,358
    #2of 68
  • Bash ReliabilityHow often the model’s bash commands succeed. Errors outside its control aren’t counted. E.g. network issues, permission denied, etc.
    Claude Sonnet 5 · 1,232Claude Sonnet 5 · 1,232Gemini 4 Neon · 1,008
    #57of 68
1,0001,1001,2001,3001,4001,5001,6001,7001,8001,900

USE CASES

  • Chat with AI
  • Build Apps & Websites
  • Write & Edit Text
  • Search the Web
  • Generate Images
  • Generate Videos
  • Chose any model
  • Compare Models Side by Side

LEADERBOARD RANKINGS

  • Overall
  • Agent
  • Alignment Index
  • Text
  • WebDev
  • Image-to-WebDev
  • Text to Image
  • Image Edit
  • Text to Video
  • Image to Video
  • Video Edit
  • Vision
  • Document
  • Search

COMPANY

  • About Us
  • How It Works
  • Blog
  • Careers
  • Leaderboard Changelog
  • Product Changelog
  • Help Center
  • FAQ

LEGAL

  • Terms
  • Privacy
  • Cookies

FOLLOW

  • X
  • LinkedIn
  • YouTube
  • Discord

© Arena Intelligence