Saturday, April 25, 2026

Sonar: AI Coding Leader Board

 Hype and Reality of the AI Coding Shift - Software Engineering Daily


Code Verification for the AI Era | Sonar


LLM Leaderboard for Code Quality & Security | Sonar


#Org
Model
Release date
Pass rate
Issue density
Lines of code
Cyclomatic complexity
Cognitive complexity
1Google
Gemini 3.1 Pro High
Feb 18, 202684.17%19.71307,703233.9158.4
2Anthropic
Claude Opus 4.5 Thinking
Nov 23, 202583.62%15.15639,465243.3121.0
3Anthropic
Claude Opus 4.7 Thinking
Apr 15, 202682.52%24.10336,283240.6171.2
4Anthropic
Claude Opus 4.6 Thinking
Feb 4, 202682.38%18.33563,574239.0133.2
5Anthropic
Claude Sonnet 4.6 Thinking
Feb 16, 202681.76%20.90627,187230.6124.8
6Google
Gemini 3 Pro
Nov 17, 202581.72%22.53289,752215.9156.4
7Anthropic
Claude Opus 4.7 High
Apr 15, 202681.65%24.38338,275241.0171.4
8Google
Gemini 3 Pro High
Nov 17, 202581.60%21.32308,553221.4160.3
9Google
Gemini 3 Flash High
Dec 16, 202581.11%20.44315,112232.8144.5
10OpenAI
GPT-5.4 Medium
Mar 4, 202681.09%26.251,177,858262.6181.8

No comments: