GPT-5 Thinking
No written verdict yet. Here is what commenters said.
6recommend
2warn against
Nov 3, 2025first mention
Apr 9, 2026latest mention
Why people recommend it
“It doesn't bullshit on the GPT-5.4 thinking version.”
“It concisely replies "GPT-5.4 Thinking".”
Show 3 more
“I used GPT-5.2-Thinking for some searches yesterday and it followed my instructions perfectly.”
“When I use GPT 5.2-thinking for my ML research job, I pretty much never encounter hallucinations.”
“I started with o3 and now I'm using 5.1 Thinking (set to max)”
switched from o3on “We gave 5 LLMs $100K to trade stocks for 8 months”
Caveats and dissent
“GPT-5.4 Thinking, Pro account.”
“So, actually, no, it cannot read it, but it believes it can.”
Often compared with
Who recommends it in their own words
Threads where it came up
- GPT-5.4 Thinking System Card 3 mentions
- The Future of Everything Is Lies, I Guess 2 mentions
- "Car Wash" test with 53 models 1 mention
- I want to wash my car. The car wash is 50 meters away. Should I walk or drive? 1 mention
- GPT-5.2 does not follow instructions and ignores my prompts 1 mention
- TimeCapsuleLLM: LLM trained only on data from 1800-1875 1 mention
Also written as GPT-5.1 Thinking, GPT-5.2 Thinking, GPT-5 Thinking, GPT-5.2-Thinking. Data: gpt-5-thinking.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 15
“GPT-5.4 Thinking, Pro account.”
“It doesn't bullshit on the GPT-5.4 thinking version.”
“It concisely replies "GPT-5.4 Thinking".”
“some non-employees have been using it for a while already”
“The actual card is here https://deploymentsafety.openai.com/gpt-5-4-thinking/introduction”
“GPT 5.2 Thinking, Standard Effort: Walk”
“GPT-5.2 Thinking: https://chatgpt.com/share/6993d099-ef4c-8005-aa62-bdb826b707a3”
“I used GPT-5.2-Thinking for some searches yesterday and it followed my instructions perfectly.”
“When I use GPT 5.2-thinking for my ML research job, I pretty much never encounter hallucinations.”
“I started with o3 and now I'm using 5.1 Thinking (set to max)”
“The 17.6% is for 5.1 Thinking High.”
“ChatGPT-5.1-Thinking one-shotted a correct Python script without any library use”
“So, actually, no, it cannot read it, but it believes it can.”
“I throw all my queries at Grok 4 Expert, GPT 5 Thinking and Opus 4.1 Extended Thinking”
“almost always opts to run a search before it attempts to answer a question”