Agent Arena 数据：长任务中模型选择可使成本相差最高 66%
跑长任务的看看这个：Arena 拿 3 万个真实任务对比了 5 家旗舰模型，Gemini 4 Carbon 比 GPT-6 Astra 每小时便宜 66%，数据很实在。
Agent Arena 统计过去 14 天内近 30000 个运行超过 1 小时的任务，模型在这些任务中平均进行 332 次工具调用。同样完成 1 小时工作，Gemini 4 Carbon 花费中位数为 10.51 美元，Claude Opus 5.5 为 21.13 美元，GPT-6 Astra 为 31.08 美元。在 5 家头部实验室的旗舰模型对比中，Claude Opus 5.5 排名 Arena 第一但耗时最长，长任务最高达 1 小时 51 分钟；Kimi K3.1 Pro 耗时最短，仅 56 分钟。数据显示长任务会放大模型之间的成本与速度差异，模型选型最高可节省 66% 成本。
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. Your browser does not support the video tag. 🔗 View on Twitter Arena.ai @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. Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 5 🔄 4 ❤️ 17 👀 3628 📊 6 ⚡
