gemini-4POST
Burkov 实测：Gemini 4 Pro 视觉推理不如 3.7 Flash
他称该模型并非世界最强，视觉推理任务上明显弱于 Gemini 3.7 Flash 和 Luna。
BURKOV
@burkov2026.09.22收录原推发布于 2026.09.22
BURKOV @burkov原推发布于 2026.09.22
Apparently not the strongest model in the world after all :-) Also, based on my tests, sucks in visual reasoning tasks compared to Gemini 3.7 Flash and Luna.
这条是引用着另一条写的：x.com/spacexai/status/2102069815225586149
x.com/burkov/status/2102163647338360931采集于 2026.09.22 10:19