Arena Launches Redesigned Leaderboard Overview
Arena launched a redesigned Leaderboard Overview that aggregates real-time evaluation signals across categories like Agents, image, and coding. Based on 354M+ sessions, Claude Fable 5.1 (Max) tops the Agent leaderboard with task costs as low as $0.04.
2026-09-25 ~ 2026-09-25 · 2 related posts
- Arena Launches Redesigned Leaderboard Hub Unifying Live Model Eval Signals — arena · 2026-09-25
- New Arena Leaderboard: Claude Fable 5.1 Tops Agents at 13.71%, Tasks From $0.04 — arena · 2026-09-25