OverviewAll LeaderboardsMethodologyComing soon
New Chat
Coding IndexGemini 4 Carbon (High)
Google

Gemini 4 Carbon (High)

Gemini 4 Carbon (High) is a proprietary model from Google. It ranks #5 of 65 models on the Coding Index with 1,297. Its best signal rank is #3 of 65, on Task Completion and Praise vs Complaint.

Coding Index Overview

Rank
#5

Rank spread 3 – 9.

Coding Index
1,297± 12
Pareto frontier
Gemini 4 Carbon
Developer
Google
License
Proprietary
Token price (in / out)
$2 / $10 per 1M
Reasoning effort
High
Sessions
16,261
Ranking updated
Nov 13, 2026

Cost, Time, and Tokens

Cost per task$2.77
GPT-6.1 Sol (Medium)$0.90AnthropicClaude Fable 5.2 (Max)$18.90

The median is $3.54.

Time per task18.4 min
AnthropicClaude Sonnet 5.5 (High)6.8 minAnthropicClaude Fable 5.2 (Max)39.4 min

The median is 19.5 min.

Output tokens per task88.6K
GPT-6.1 Sol (Medium)29.4KAnthropicClaude Sonnet 5.5 (Max)264.8K

The median is 88.6K.

Coding Ranking

1,0001,1001,2001,3001,4001,5001,600
  1. 1,533
    Anthropic
    Claude Fable 5.2Max#1
  2. 1,374
    Anthropic
    Claude Opus 5.5Max#2
  3. 1,307
    Anthropic
    Claude Opus 5.5High#3
  4. 1,304
    Anthropic
    Claude Sonnet 5.5Max#4
  5. 1,297
    Gemini 4 CarbonHigh#5
  6. 1,281
    GPT-6 AstraMax#6
  7. 1,280
    GPT-6.1 TerraMax#7
  8. 1,272
    Anthropic
    Claude Fable 5.1Max#8
  9. 1,259
    Gemini 4 HydrogenHigh#9
  10. 1,258
    GPT-6.1 SolMax#10
  11. 1,236
    Anthropic
    Claude Sonnet 5.5High#11
  12. 1,227
    GPT-6.1 SolMedium#12
  13. 1,226
    GPT-6 SolMax#13
  14. 1,212
    Meta
    Muse Wonder FullMax#14
  15. 1,208
    Gemini 4 ArgonHigh#15

Signal Performance

Gemini 4 CarbonLeader
Rank on the board
  • Task CompletionHow often the model gets users to confirm the task is done.
    Claude Sonnet 5.5 (Max) · 1,356Claude Sonnet 5.5 (Max) · 1,356Gemini 4 Carbon · 1,298
    #3of 65
  • Praise vs ComplaintHow often the model earns more explicitly positive responses than negative ones.
    Claude Fable 5.2 · 2,017Claude Fable 5.2 · 2,017Gemini 4 Carbon · 1,440
    #3of 65
  • SteerabilityHow well the model lands user corrections when they push back.
    Claude Fable 5.2 · 1,454Claude Fable 5.2 · 1,454Gemini 4 Carbon · 1,299
    #5of 65
  • 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 · 1,234Claude Sonnet 5 · 1,234Gemini 4 Carbon · 1,003
    #57of 65
9001,0001,1001,2001,3001,4001,5001,6001,7001,8001,9002,0002,100

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