# Arena finds a 55-minute gap in long-horizon task time among top models

> Original title: Agent Arena measures complex, real-world tasks. Data shows that these long-horizon sessions amplify differences in frontier models.

- Source: Arena
- Published: 2026-11-04T17:30:11.000Z
- Bad Influence: https://badinfluence.news/items/byhv7oxymg8irlttfa1dek1gl
- Original: https://x.com/arena/status/2118033077121524129

## Summary

Arena's Agent Arena comparison of the top model from each of five leading labs shows a 55-minute gap in time spent on long-horizon tasks. Claude Opus 5.5, ranked #1 on Agent Arena, takes the longest at every task length, peaking at 1 hour 51 minutes. Kimi K3.1 Pro spends the least time at every length, with 56 minutes on long-horizon tasks.

## Post

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.

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2118031505796784128%2Fimg%2F0Oqwl8jRwdAUC0Yy.jpg&mode=thumb&exp=1794009600&sig=e37e468a550161d9)