← All models

Gemini · Last 7 days

Gemini 3.7 Flash

0–100 · higher means more positive community experience, not benchmark performance.

Updated 2026-09-05 14:21 UTC · 2026-08-29 – 2026-09-05 UTC
Community score46.8/10032 comments in 7 days

Community reviews

Selected comments from the last 7 days. The balance of excerpts does not represent the share of positive reviews.

7 selected excerpts

NegativeCoding

“gemini flash 3.7 42/100”

NegativeReasoning

“Gemini 3.7 Flash, Composer 2.5 → Speed. Hallucinations. Impreciseness. They are cheap and fast, perfect for small UI and text changes or small corrections, but if you give them task that's more complicated or requires taste, expect slop.”

NegativeReasoning

“Gemini 3.7 Flash is still very LLM-y as it often doesn't seem to the take the given context into consideration and consistently hallucinates”

NegativeSpeed & latency

“meanwhile gemini flash 3.7 is not faster, no idea what is going on. it takes endless with minimum context.. and my connection is great.”

NegativeSpeed & latency

“gemini 3.7 flash with google ai studio API is ~130 token/s, google vertex API is ~80 token/s, who is going to make up the 3-6x speed difference I need”

ZhihuzhMachine translated
Show original

gemini 3.7 flash用google ai studio的API在~130 token/s,google vertex的API在~80 token/s,我缺的3-6倍速度谁给我补上

NegativeSpeed & latency

“Gemini 3.7 flash outputs so many tokens per answer it doesn't matter how fast its TPS is, sol will end up being both cheaper and faster than Gemini”

NegativeRoleplay / creative

“A professional screenwriter told me that Gemini 3.7 Flash is really not useful for creative assistance, can only be used like Baidu.”

ZhihuzhMachine translated
Show original

专业编剧告诉我,Gemini 3.7 Flash在创作辅助上是真没什么用,只能当百度来用。