# Gemini 3.5 Flash速度与agent能力提升，但成本显著增加

- 来源：Artificial Analysis (@ArtificialAnlys)
- 发布时间：2026-05-27 00:49
- AIHOT 分数：60
- AIHOT 链接：https://aihot.virxact.com/items/cmpmw18vt0sddsl014b7mhoj8
- 原文链接：https://x.com/ArtificialAnlys/status/2059316050391634302

## AI 摘要

Gemini 3.5 Flash在速度与agent能力上实现进步，实测输出速度可达约280 output tokens/sec，在GDPVal-AA agent任务中ELO提升至约1650，相比Gemini 3 Flash有显著提升。但代价是成本增加约5倍，主要因token单价上涨（为Gemini 3.5 Flash的3倍）以及使用量更高。

## 正文

Gemini 3.5 Flash is a step forward for Google on speed and agentic capabilities but comes at a trade-off of being higher cost than prior models

We have measured up to ~280 output tokens/sec， placing it on the speed/intelligence Pareto frontier and well ahead of Gemini 3 Flash. It also shows a major uplift on agentic tasks， reaching ~1650 ELO on GDPVal-AA.

The trade-off： cost is up ~5x versus Gemini 3 Flash， driven by higher token prices （3x higher than Gemini 3 Flash） and higher token usage.

In this video， Declan Jackson， Member of Technical Staff at Artificial Analysis， breaks it down.