ModelsMulti-source

LMArena 推出 Agent Arena Index:Gemini 4 Neon 首秀第 2,GPT-6.2 双版本入榜

This Week in the Arena: We launched the Agent Arena Index, where Gemini 4 Neon landed #2, and GPT-6....

Why we picked it

这期周报信息量不小:Gemini 4 Neon 一上来就冲到智能体榜第 2,GPT-6.2 两个版本一个走性能一个走价格。做智能体选型的开发者可以直接拿这份榜单当采购参考,Qwen4-Max 拿下中国模型头名也值得留意。

LMArena 本周发布全新 Agent Arena Index 智能体排行榜。Google DeepMind 的 Gemini 4 Neon (High) 首次上榜即以 1336 分拿下第 2 名,OpenAI 的 GPT-6.2 Astra (Max) 以 1291 分排在第 6,同系列的 GPT-6.2 Sol (Max) 以 1241 分位列第 11。

Image · lmarena.ai
Body

Sol 同时进入成本前沿,每任务中位成本为 0.90 美元。Alibaba Qwen 的 Qwen4-Max (xHigh) 首秀排在总榜第 14 位,是目前排名最高的中国模型。Microsoft AI 的 MAI-Image-2.7 结束预览阶段,在 Multi-Image Edit 类目拿第 3 名,单图成本 0.035 美元。

其他更新方面,Amazon 基于 AgentCore Web Search 的 Web-Search-Agent 登顶 Search Arena;Meta 的 Muse Ember (Max) 在 Code Arena: WebDev 拿到 1608 分,中位成本约 0.03 美元每任务,相比此前同价位最佳的 1438 分有明显提升。

Original · lmarena.ai

This Week in the Arena: We launched the Agent Arena Index, where Gemini 4 Neon landed #2, and GPT-6....

This Week in the Arena: We launched the Agent Arena Index, where Gemini 4 Neon landed #2 , and GPT-6.2 Astra and Sol landed #6 and #11 ! - Gemini 4 Neon (High) by @GoogleDeepMind debuted at #2 with 1336 points on the new Agent Arena Index! More info on this launch in thread. - GPT-6.2 Astra (Max) by @OpenAI entered at #6 with 1291 points, while GPT-6.2 Sol (Max) entered at #11 with 1241. Sol joined the cost frontier at a $0.90 median cost per task. - Qwen4-Max (xHigh) by @Alibaba_Qwen debuted at #14 overall, and as the #1 Chinese model. - MAI-Image-2.7 by @MicrosoftAI left preview and landed #3 in Multi-Image Edit, and joined the cost frontier at $0.035 per image. - Amazon-Web-Search-Agent with AgentCore Web Search by @amazon took #1 in Search Arena. - Muse Ember (Max) by @AIatMeta scored 1608 pts in Code Arena: WebDev and landed on the Pareto frontier at about $0.03 median cost per task, up from the previous best of 1438 pts at a similar price. Watch this week’s recap! youtube.com/live/qQUc_r5f4…📊 12 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Gemini 4 Neon, GPT-6.2, Qwen4-Max, LMArena.

Source attribution: curated from lmarena.ai (@lmarena_ai). Cross-source corroboration: 11 independent sources have covered this development (including Artificial Analysis, 宝玉, OpenRouter), confirming industry-wide signal strength.