模型多源确认

Gemini Argon 4 在 LiveBench 2.0 上落后 Fable 与 Astra,仍领先开源模型

精选理由

用 LiveBench 2.0 给 Gemini Argon 4、GPT 6.1 Sol 和 DeepSeek Flash 排了个序,榜单自称难刷分,可以看看结果信不信得过。

Gemini Argon 4.0 在自建的 LiveBench 2.0 基准上落后于 GPT 6.1 Sol,也排在前面的 Fable 和 Astra 之后。该模型仍领先开源的 DeepSeek Flash,并明显优于 Muse Wonder,而 Muse 只比 DeepSeek 略好。发布方称 LiveBench 2.0 难以刷分,更接近真实使用场景。

原文 · Bindu Reddy

🚨 Gemini Argon 4 Falls Behind Fable And Astra, But Is Ahead of Open Source

- Argon 4.0 falls short of GPT 6.1 Sol - ahead of open-source (Deepseek Flash) - much better than Muse Wonder - Muse is marginally better than DeepSeek

This is all on our new benchmark, which can't be benchmaxxed easily and reflects real-world usage - LiveBench 2.0