Artificial Analysis 评测 Google 10 月 6 日发布的新图像模型 Nano Banana 2.1,该模型基于 Gemini 3.6 Flash,在 AA-Image-T2I v2.0 和 AA-Image-Editing v2.0 上均排名第 4,在所测 16 项生成与编辑能力上全面高于前代。
评测方给出了 Nano Banana 2.1 在文生图和图像编辑榜的排名、16 项能力变化和各分辨率价格,读者可据此比较它对现有工作流的适用性。
Google's Nano Banana 2.1 takes #4 on both AA-Image-T2I v2.0 and AA-Image-Editing v2.0, at half the price of Nano Banana 2
Nano Banana 2.1 is Google's new image model, released on October 6. It is based on Gemini 3.6 Flash and replaces Nano Banana 2 (Gemini 3.1 Flash Image) on the Gemini API. It supports both Text to Image and Image Editing in one model. We evaluated Nano Banana 2.1 through the Gemini API at 1K resolution with default settings.
Nano Banana 2.1 is a significant improvement over Nano Banana 2: it ranks higher in all 16 of the generation and editing capabilities we measure, with the largest gains in the Retail & Ecommerce and Productivity & Knowledge Work use cases.
Nano Banana 2.1 is priced at $0.0336 per image ($33.6 per 1k images) at 1K resolution on the Gemini API. That is half the 1K price of Nano Banana 2, and the lowest price among the top 7 models on AA-Image-T2I v2.0. At 2K it costs $0.0504 per image, and at 4K $0.0756 per image.
Nano Banana 2.1 is available in the Gemini app, AI Mode in Search, Google AI Studio, Flow, Stitch, Google Ads and Gemini Enterprise Platform, through the Gemini API and Vertex AI, and on third-party providers.
Congratulations to @GoogleDeepMind & @Google on the release!
See below for our detailed analysis and example outputs of Nano Banana 2.1 in the Artificial Analysis Image Arena 🧵
来源:Artificial Analysis · x.com