最新资讯
bloomberg.com 台积电据报考虑生产先进 AI 存储芯片 www.infoq.com Yelp 为 AI Assistant 融合原生与服务器驱动 UI computerworld.com 英国监管机构:企业须为自家 AI 代理的错误负责 siliconangle.com Atomicwork 推出面向企业 IT 与安全的认证 AI 同事市场 computerworld.com OpenAI 收购小型软件公司以改进 Codex bdtechtalks.com Next-Concept Modeling 如何重新思考 AI 文本生成 computerworld.com Box 发布 Architect:用自然语言构建业务流程工作流 techrepublic.com Perplexity 推出 Teammates:每月 200 美元的 AI Agent 如何工作 the-decoder.com METR 称 Anthropic 或已在 7 月越过自身 AI 加速预警阈值 towardsdatascience.com 用 Ollama 和 Python 构建你的第一个多工具 AI Agent the-decoder.com Thinking Machines 的 Inkling 2 Small 称霸西方开放权重模型 dev.to 为 CI/CD 构建 AI 质量门禁
多元动态
登录 注册
智能体 x.com · @lmarena.ai(@lmarena_ai)

Agent Arena 榜单更新:GPT-6 Luna (Max) 以每任务 0.05 美元进入帕累托前沿

原文 我的收藏

LMArena 的 Agent Arena 更新显示,OpenAI 的 GPT-6 Luna (Max) 以 +1.59% 净提升、每任务中位成本 0.05 美元进入帕累托前沿。其成本比 DeepSeek-V4.1-Flash 低 29%、比 Hy4 preview 低 76%,净提升分仅落后两者 2.27 和 2.51 个百分点;相比同在前沿的 GPT 模型,成本比 GPT-6 Sol (Max) 低 94%、比 GPT-6 Astra (Max) 低 98%。该模型在 Agent Arena 总榜列第 23,较 GPT-5.6 Luna (xHigh) 提升六位,主要增益来自 Confirmed Success 与 Bash Recovery 两项信号。

AI推荐理由 LMArena 官方账号给出 Agent Arena 榜单更新,含 GPT-6 Luna (Max) 的净提升 +1.59%、每任务中位成本 0.05 美元,以及与 DeepSeek-V4.1-Flash、Hy4 preview、GPT-6 Sol/Astra 的成本对比和分项信号(Confirmed Success、Bash Recovery)。数据具体、可对照,但为榜单方自述且引用的是其自身评测口径,需注意其排名与成本结论的适用范围。

70

正文

Update to the Agent Arena Pareto frontier: GPT-6 Luna (Max) has landed on the Agent Arena Pareto frontier with +1.59% net improvement at a median cost of just $0.05 per task! Luna costs 29% less than DeepSeek-V4.1-Flash and 76% less than Hy4 preview, while trailing their net-improvement scores by just 2.27 and 2.51 percentage points respectively. Compared to other GPT models on the Pareto frontier, GPT-6 Luna (Max) costs 94% less than GPT-6 Sol (Max), and 98% less than GPT-6 Astra (Max). Congrats to the [@OpenAI](https://x.com/OpenAI) team on this cost-efficient release! ![Tweet Image](https://pbs.twimg.com/media/HTVt-7_bcAAQZhP.jpg) ![Arena.ai](https://pbs.twimg.com/profile_images/2017015061454438400/iNKfXZ_I_normal.jpg) Arena.ai@arena GPT-6 Luna (Max) by [@OpenAI](https://x.com/OpenAI) is #23 in Agent Arena with +1.6% net improvement across 8K real-world agentic sessions from our global community of users. Although GPT-6 Luna (Max) did not land on the Agent Arena Pareto frontier, it remains a cost-efficient model. Its $0.05 median cost per task is 94% lower than GPT-6 Sol (Max) at $0.82 and 98% lower than GPT-6 Astra (Max) at $2.59. Its net-improvement score also comes within 0.09 percentage points of #22 GPT 5.5, while costing 91% less than its $0.56 median cost per task. This release is a six-place point-rank move over GPT-5.6 Luna (xHigh), at -0.9% and #29! By signal, GPT-6 Luna’s clearest gains over GPT-5.6 Luna are in: - Confirmed Success: #17 (+4.6%) vs. #33 (-4.6%) - Bash Recovery: #21 (+4.2%) vs. #27 (+2.2%) Congrats to the [@OpenAI](https://x.com/OpenAI) team on this release! ![Tweet Image](https://pbs.twimg.com/media/HTVMuGnaIAEi9Vq.jpg) [🔗 View Quoted Tweet](https://x.com/arena/status/2104673568776990762) 💬10🔄3❤️34👀7142📊10

来源报道 · 1 篇 · 以下链接均前往原始媒体

← 返回精选动态 原文

更多内容