LMArena 推出 Agent 排行，GPT 5.5 (High) 拔得头筹

星***

Arena Blog – 4 Jun 26 (https://arena.ai/blog/agent-arena-methodology/)

Agent Arena: Causal Evaluation of Agents in the Real World (https://arena.ai/blog/agent-arena-methodology/)
Agents are increasingly doing real work. The resulting task distribution has greatly expanded. We desire an agent evaluation that scales along with usage and capability.

Agent Arena: AI Model Agentic Performance Leaderboard (https://arena.ai/leaderboard/agent)

Agent Arena: AI Model Agentic Performance Leaderboard (https://arena.ai/leaderboard/agent)
Dynamic ranking of models on how well they orchestrate tools for real-world agentic tasks, based on signals like tool reliability, task completion, and steerability.