Agent Arena 用跨数百轮的长周期任务（如代码库迁移至 Rust、投资策略文档审计、撰写数学教材）评测模型，发现前沿模型差异被放大。五大实验室各自最强模型在长任务耗时上相差 55 分钟：排名第一的 Claude Opus 5.5 在各任务长度下耗时最长，峰值达 1 小时 51 分钟；Kimi K3.1 Pro 耗时最短，长任务仅 56 分钟。
Agent Arena measures complex, real-world tasks. Data shows that these long-horizon sessions amplify differences in frontier models.
Long-horizon tasks in Agent Arena span hundreds of turns, from porting a codebase to Rust and auditing an investment strategy document to writing a math textbook, and more.
Comparing the top model from each of the 5 leading labs on Agent Arena reveals a 55-minute gap in how long they spend on long-horizon tasks. The models are:
- Claude Opus 5.5 by @AnthropicAI
- Gemini 4 Carbon by @GoogleDeepMind
- GPT-6 Astra by @OpenAI
- Muse Wonder Full by @AIatMeta
- Kimi K3.1 Pro by @Kimi_Moonshot
In this group, Claude Opus 5.5, #1 in Agent Arena, takes the longest at every task length, peaking at 1 hour 51 minutes. In contrast, Kimi K3.1 Pro spends the least time at every length, with 56 minutes on long-horizon tasks.
来源：Arena.ai · x.com