gemini-4IMAGE
报道称 Gemini 4 跑分与实战有落差
记者爆料:Gemini 4 基准分数和真实任务(含部分编程)表现存在差距,内部对是否追平 OpenAI、Anthropic 意见不一。
Davey Alba
@daveyalba28 天前收录原推发布于 2026.10.01

Davey Alba @daveyalba原推发布于 2026.10.01
NEW: As Google unveils Gemini 4, sources tell us there's a gap b/w how it scores on benchmarks and how it performs on real-world tasks, including certain coding work. Internally, opinions are mixed on whether it has caught up to OpenAI & Anthropic. Scoop w/@byJuliaLove @EdLudlow
x.com/daveyalba/status/2105398718178443512采集于 2026.10.01 10:02