Agent Arena Leaderboard: Claude Opus 5 Leads, Kimi K3 Enters Top 5

arena · x · 2026-08-05

Agent Arena released its latest leaderboard, evaluating 45 models across 1.6 million sessions on real-world agentic tasks. Claude Opus 5 (High) tops with a 12.10% net improvement, followed by Claude Fable 5 (High) and Claude Opus 5 (Max). Kimi K3 (Max) ranks fourth at 10.18%, and GPT-5.6 Sol is fifth at 10.09%. The board includes metrics like tool hallucination rate and steerability.

Original post →

More from Models

Models channel →