跳到正文
𝕏 Arena.ai(x.com)·· 18 天前精選品質評分68
重點導讀

Arena.ai 分享 Agent Arena 長時程任務的成本比較:近 14 天有近 30,000 項任務執行超過 1 小時,每小時平均呼叫工具 332 次。

AI 伴隨問答

自備 Key 深度分析

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:

推薦理由

近 30,000 項長時程任務的成本資料,呈現 Gemini 4 Carbon、Claude Opus 5.5 與 GPT-6 Astra 在每小時工作費用和評分上的取捨。

Arena.ai
Arena.ai@arena
·18 天前
𝕏

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.

推文來源 · X (Twitter)在 X 參與討論
來源: Arena.ai (x.com)
在 X 查看推文

讀者討論

理性交流 · 即時討論