# Arena finds Gemini 4 Carbon costs half as much as Claude Opus 5.5 per hour

> Original title: In the last 14 days, nearly 30,000 tasks ran for over an hour on Agent Arena. Within that hour, the average model made 332 tool calls.

- Source: Arena
- Published: 2026-11-04T17:49:24.000Z
- Bad Influence: https://badinfluence.news/items/s72a3mn1bawtmft5ftezsmxfj
- Original: https://x.com/arena/status/2118037914512990506

## Summary

Arena reports that Gemini 4 Carbon costs a median $10.51 per hour-long task on Agent Arena, versus $21.13 for Claude Opus 5.5 and $31.08 for GPT-6 Astra. Arena says Claude Opus 5.5 still scores higher but costs twice as much per hour of work. The comparison covers nearly 30,000 tasks run for over an hour in the last 14 days, averaging 332 tool calls per task.

## Post

In the last 14 days, nearly 30,000 tasks ran for over an hour on Agent Arena. Within that hour, the average model made 332 tool calls.

In these long-horizon tasks, the right model choice can cut the cost by up to 66%.

In Agent Arena, an hour of work costs a median $10.51 per task with Gemini 4 Carbon, $21.13 with Claude Opus 5.5 by @AnthropicAI and $31.08 with GPT-6 Astra by @OpenAI. 

That makes Gemini 4 Carbon by @GoogleDeepmind 50% cheaper than Opus and 66% cheaper than Astra for an hour-long task.

For long-running jobs, weighing cost against capability becomes critical: Claude Opus 5.5 still scores higher, but costs twice as much per hour of work.

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2118037801644281856%2Fimg%2F_o2YRt3nCcNkSZt4.jpg&mode=thumb&exp=1794009600&sig=d16bdb753568348e)

## Quoted post @arena

> 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.

https://x.com/arena/status/2118033077121524129