ainewsblitz.com

Breaking

Agent Arena Data Shows Claude Opus Gains Come With Sharply Higher Token Use

Agent Arena Data Shows Claude Opus Gains Come With Sharply Higher Token Use
  • Foundation Models
  • AI Agents
  • Research & Papers

As Anthropic's Claude Opus series climbed from version 4.7 to 5, its real-world task performance improved markedly—but the number of tokens consumed to finish those tasks rose even faster, according to tracking data from the agentic-evaluation platform Agent Arena.

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 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year