ainewsblitz.com

Breaking

Anthropic's Claude Sonnet 5 Takes No.6 on Code Arena Frontend, Up 29 Points on Predecessor

  • Foundation Models
  • Software Dev & Coding
  • AI Agents

The thinking version of Claude Sonnet 5, released by Anthropic on June 30, 2026, has ranked No.6 (score 1551) on Code Arena: Frontend, which evaluates agentic frontend web development. It topped its predecessor Sonnet 4.6 (No.13, 1522) by +29 points and even edged out the higher-tier Opus 4.6 (Thinking) by +9 points. The Arena.ai leaderboard uses ELO ratings from more than 420,000 anonymous head-to-head votes and is closely watched as a real-world comparison of models on frontend web development tasks.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 9,810 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year