GPT · 近 7 天
GPT-6 Sol
0–100 分，越高代表社区使用体验越正面，不代表能力测试成绩。
更新于 2026-10-01 12:57 UTC · 2026-09-24 – 2026-10-01 UTC体感分28.3/100307 条评论 · 近 7 天
大家怎么看
有用户认为GPT-6.1 Sol还不如GPT-6 Sol，间接肯定GPT-6 Sol更出色。有用户使用 GPT-6 Sol 生成 C++ 代码时，代码经常过于冗长、不够简洁或简单，需要多轮清理。
样本与评分说明
截至 2026-10-01 13:07:02 UTC，GPT 家族的 GPT-6 Sol 在近 7 天有 307 条明确归属该版本的社区反馈，社区口碑分为 28.3/100。部分有效分类评分：通用文本 24.3/100 (n=170)；编程 35.4/100 (n=23)；推理 32.0/100 (n=46)。 评分方法与数据来源
社区评论
精选近 7 天的不同意见，摘录条数不代表真实好评比例。
2 条精选摘录
额度评价来自社区体验，不能据此推算官方实际配额。
展开原文
i’ve noticed this since GPT-6 SOL and honestly I do not mind the work taking longer for it to complete as long as I get more usage out of it.
查看评论上下文
GPT-6.1 sol 新变化
展开原文
Generated code (I mostly program C++) is often bloated and not succinct or "simple" enough to my tastes
展开原文
took 80% of the pro plan in 3 tasks
展开原文
Now this feels like its the actual Sol 6 that was meant to be.
查看评论上下文
我有一种感觉，GPT 6 Sol 实际上是 GTP 6 Terra，它感觉不如 Sol 好，基准测试也显示它比之前的 Sol 版本稍差。
机器翻译展开原文
I had the feeling that GPT 6 Sol was actually GTP 6 Terra, it didn't felt as good as Sol, and the benchmarks also showed it was a bit worse than the previous Sol release.
展开原文
I dont trust code reviews by it
展开原文
GPT 6 Sol still beat Opus 5.5 on code review
查看评论上下文
在我昨天的测试中，GPT 6 Sol在代码审查（本次测试中为GPT编写的代码）方面仍然击败了Opus 5.5，6.1可能会表现得更好。
机器翻译展开原文
In my testing yesterday GPT 6 Sol still beat Opus 5.5 on code review (of GPT written code in this case) 6.1 will probably perform even better.
展开原文
After a banked reset your weekly usage gets cut by about 80%
展开原文
6-Sol is noticeably worse for code reviews
展开原文
twice as much usage on Sol (which is equivalent to what you use to get on Sol anyways
展开原文
GPT 6 Sol has been borderline unusable today for me, extremely slow, doesn't follow instructions, and is writing very stupid code. I tried 5.6 Sol as well and it seemed to have the same issue.
展开原文
It completely erases my anxiety about the usage limit
展开原文
6 can at least get through to the end
查看评论上下文
5.6 sol 总是跑题，或者把自己想进死胡同。
机器翻译展开原文
5.6 sol always goes off on tangents or thinks itself into a corner.
展开原文
sol made some really brain-dead decisions - even though I had a pretty detailed plan
展开原文
ignore your instructions in implementation
展开原文
6 Sol did a better job reviewing and configuring my AWS setup than 5.6 did
展开原文
I made GPT 6 Sol orchestrate a GPT 6 Luna to implement something on a music player I'm working on, it took around 20 minutes and spent only 1% of my weekly usage.
展开原文
I can get 72hours or more of usage running both at the same time
查看评论上下文
我不理解人们遇到的用量问题。
机器翻译展开原文
I’m not understanding the usage issues people are experiencing.
我让 codex 和 chatgpt 以 daybreak high 和 gpt-6 sol 全天候运行 24 小时，同时运行两者可以获得 72 小时或更长的使用时间
机器翻译展开原文
I run codex and chatgpt 24 hours on daybreak high and gpt-6 sol and I can get 72hours or more of usage running both at the same time
展开原文
GPT 6 sol, while it seems to be controversial, can go on for seemingly forever
展开原文
on med or even high it makes errors with xhigh i find it surprisingly capable of self correcting
展开原文
no safeguards observed
近 7 天暂时没有符合此筛选条件的精选评论。