Agent Arena 的資料顯示,長程任務會放大前沿模型的表現差異,任務涵蓋數百輪互動,從移植程式碼至 Rust 到撰寫數學教科書。
- 耗時比較:五家領先實驗室的模型在長程任務上相差 55 分鐘;排名第 1 的 Claude Opus 5.5 耗時最久,最高達 1 小時 51 分鐘,Kimi K3.1 Pro 最短,為 56 分鐘。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
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.