大模型
x.com ·
@Arena.ai (@arena)
LMArena：Gemini 4 Argon (High) 登顶 Text Arena，1525 分并刷新性价比前沿
LMArena 称 Google DeepMind 的 Gemini 4 Argon (High) 在 Text Arena 以 1525 分排名第一，在 Code Arena: WebDev 以 1679 分排名第八，混合价格 $8/MToken，被描述为当前最具成本效率的模型。该模型在 Coding、Hard Prompts、Instruction Following、Longer Query、Creative Writing 以及各职业领域、英语、非英语、中文、俄语等子项均列第一，比第二名 Claude Opus 4.6 (High) 高 20 分；在 WebDev 榜较 Gemini 3.8 Flash (High) 提升 96 分，从第 29 升至第 8。以上均为 LMArena 单方榜单数据，评测细节与模型版本未在输入中给出。
AI推荐理由 LMArena 官方账号发布的榜单结果，给出了 Gemini 4 Argon (High) 在 Text Arena 1525 分、Code Arena: WebDev 1679 分、混合价格 $8/MToken 等具体数字，并称其在 Coding、Hard Prompts、Instruction Following 等子项排名第一，比第二名 Claude Opus 4.6 (High) 高 20 分。这些是可核对的竞技场排名与价格信息，对模型选型有参考价值。但内容为榜单方自述，未提供评测方法、样本量或独立复现，且模型名称与版本号（Gemini 4 Argon、Claude Opus 4.6、Gemini 3.8 Flash）无法从输入中验证，需保留不确定性。
72
浏览 569,551
点赞 2,959
评论 103
转发 286
正文
Big news: Gemini 4 Argon (High) by @GoogleDeepMind just landed #1 in Text Arena with 1525 pts, and #8 in Code Arena: WebDev with 1679 pts!
This release has reshaped the Text Arena Pareto frontier with a blended $8/MToken! Gemini 4 Argon (High) is now the most cost efficient model, see its placement on Pareto frontier below.
In the Text Arena, Gemini 4 Argon (High) ranks #1 in Coding, Hard Prompts, Instruction Following, Longer Query, and Creative Writing. It also leads every occupational domain evaluated, with additional #1 spots in English, Non-English, Chinese, and Russian.
This model is +20 points above the #2 ranked Claude Opus 4.6 (High), and a huge leap from Google’s previous release, Gemini 3.8 Flash (High) at #11!
In Code Arena: WebDev, Gemini 4 Argon (High) gained +96 points from Gemini 3.8 Flash (High), and went from #29 to #8.
Congrats to the @GoogleDeepMind team on this impressive frontier release!