精选模型78

Arena 实测 Gemini 4 Neon 在 3D、游戏与 UI 上的表现

原标题:Just yesterday, @GoogleDeepMind released Gemini 4 Neon.

Arena.ai@arena发布时间 (北京时间)

Arena.ai 发布视频,由 Peter Gostev 首次上手 Google DeepMind 昨日发布的 Gemini 4 Neon,在 3D 场景、游戏、UI 和数据可视化等任务中实测,并与 Opus、Fable、Astra、Sol 对比。

推荐理由视频以 3D 场景、游戏、UI 和数据可视化等实测,对比 Gemini 4 Neon 与 Opus、Fable 等模型在前沿能力上的差距。

Just yesterday, @GoogleDeepMind released Gemini 4 Neon.

Watch @petergostev’s first impressions as he unboxes this new model across 3D scenes, games, UIs and data visualizations. He compares it with Opus, Fable, Astra and Sol and shares his take on how close it is to the frontier.

00:00 Introduction and Arena ranking
00:29 Istanbul: first comparisons
01:38 White House and 3D detail
06:38 Creativity, realism and complex scenes
11:57 Live Aid and cinematic movement
13:38 Games: controls and visual quality
15:40 UI and design comparisons
17:02 Data visualization
18:03 UI coherence and design quality
21:59 Dynamic data and consistency
23:36 Pricing and model comparisons
27:30 Final verdict: how close to the frontier?

重大消息:Gemini 4 Neon (High) 是 Agent Arena Index 上表现最好的 @GoogleDeepmind 模型,综合排名第2,并重塑了帕累托前沿! 基于 Arena 全球社区 4.2k 个真实世界智能体会话,它获得 1336 分,超越了: - 第4名 Carbon (High):1303 分 - 第9名 Hydrogen (High):1271 分 - 第11名 Argon (High):1229 分 Neon 以每任务中位成本 $2.82 位于 Agent Arena 帕累托前沿。它的得分高于第3名 Claude Opus 5.5 (Max),而每任务成本低 53%;相比第1名 Claude Fable 5.2 (Max),每任务成本低 69%。帕累托图见本帖。 它在关键信号上表现强劲: - 第2名 赞扬 vs. 投诉:1539 分(用户对智能体结果的满意度) - 第2名 可引导性:1298 分(智能体对用户纠正的响应程度) - 第3名 任务完成:1316 分(用户明确确认任务成功) 它在 Code Arena:WebDev 和 Text Arena 中的排名见本帖下方。 祝贺 @GoogleDeepmind 团队又发布了一个重磅版本!
查看原文

Big news: Gemini 4 Neon (High) is the best @GoogleDeepmind model on the Agent Arena Index, ranking #2 overall and reshaping the Pareto frontier! With 1336 pts based on 4.2k real-world agentic sessions from Arena’s global community, it surpassed: - #4 Carbon (High): 1303 pts - #9 Hydrogen (High): 1271 pts - #11 Argon (High): 1229 pts Neon is on the Agent Arena Pareto frontier at $2.82 median cost per task. It scores higher than #3 Claude Opus 5.5 (Max) for 53% less per task, and is 69% less per task than #1 Claude Fable 5.2 (Max). See Pareto in thread. It's strong across key signals: - #2 Praise vs. Complaint: 1539 pts (user satisfaction with the agent’s outcome) - #2 Steerability: 1298 pts (how well an agent responds to user corrections) - #3 Task Completion: 1316 pts (explicit confirmation of task success from users) See where it landed in the Code Arena: WebDev and Text Arena below in thread. Congrats to the team at @GoogleDeepmind on another huge release!

查看原帖