智能体
x.com ·
@omarsar0
Composio 评测:Pareto 26.9 在 30 个 agent 任务中与 GPT-6 Astra 并列第一,成本约三分之一
elvis 转述 Composio 的评测结果:Pareto 26.9 将请求发送给多个前沿和开源模型并保留最佳答案,在 30 个 agent 任务的新评测中与 GPT-6 Astra 并列第一,每成功任务成本约为其三分之一,完成任务速度也快于 DeepSeek V4 Pro 和 GLM 5.3 Flash。Composio 称测试了 GPT-6 Astra、Opus 5.5、GPT-6 Sol、Pareto 26.9、DeepSeek V4 Pro 和 GLM 5.3 Flash 六款模型,其中 Sol 得分与 Opus 相当、速度更快、每成功任务成本约为其四分之一。
AI推荐理由 转述 Composio 对 6 个模型在 30 个 agent 任务上的评测,称 Pareto 26.9 与 GPT-6 Astra 并列第一且每成功任务成本约为其三分之一,并比 DeepSeek V4 Pro 和 GLM 5.3 Flash 更快。涉及模型对比与成本效率,对 agent 工作负载选型有参考价值,但为第三方转述,未提供完整评测方法或原始数据,需保留不确定性。
68
浏览 2,712
点赞 13
评论 5
转发 1
正文
Interesting results here. This is why I expect more agent workloads to run on blended models.
Pareto 26.9 from [@TheUnbiasedCo](https://x.com/TheUnbiasedCo) sends requests to several frontier and open models and keeps the best answer.
In the new eval of 30 agent tasks, Pareto tied GPT-6 Astra for first place at about 1/3 the cost per successful task.
It also finished tasks faster than DeepSeek V4 Pro and GLM 5.3 Flash.

Composio@composio
We tested 6 AI models on 30 challenging agent tasks: GPT-6 Astra, Opus 5.5, GPT-6 Sol, Pareto 26.9, DeepSeek V4 Pro, and GLM 5.3 Flash.
Sol matched Opus’s score, finished faster, and cost about a quarter as much per successful task.
Here’s how all 6 models compared 🧵🧵🧵

[🔗 View Quoted Tweet](https://x.com/composio/status/2103123792893755807)