Claude 4.5 (Anthropic)
Hacker ApprovedRanked 28 of 72 language models by recommenders
People recommend it for strong coding and chat output, with fast, clean results and a good feel to use. The most common caveat is that it still makes mistakes and needs close supervision on complex codebases.
People recommend it for strong coding and chat output, with fast, clean results and a good feel to use. The most common caveat is that it still makes mistakes and needs close supervision on complex codebases.
43 people gave an opinion
- recommend it
- 32
- criticize it
- 11
- approval share
- 74%
Recommended in 11 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 32 people recommend itNeeds 10 or more, met.
- 2.9 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 11 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Strong coding and task performance
“There are tasks that you'd have to reroll 3.5 til the end of the universe that 4.5 would one shot.”
Comment from 17 Jan 2026 in “The Death of Software Development” “For the work I am doing, I found Claude 4.5 (both models) to be absolutely unchallenged.”
Comment from 29 Nov 2025 in “Google CEO Pushes 'Vibe Coding' – But Real Developers Know It's Not Magic” “It tends to produce very good, clean, well-documented code and tests.”
Comment from 20 Dec 2025 in “Ask HN: Are you afraid of AI making you unemployable within the next few years?” - Comment from 15 Jan 2026 in “Anthropic Explicitly Blocking OpenCode”
Fast and efficient to use
“I also feel like 4.5 was just way more efficient too”
Comment from 18 Feb 2026 in “Claude Sonnet 4.6 System Card” “Claude 4.5 is by far the best/fastest coding model”
Comment from 15 Jan 2026 in “Anthropic Explicitly Blocking OpenCode” Good feel and tooling
“Much better feel with the Claude 4.5 series, for both chat and coding.”
Comment from 30 Jan 2026 in “Retiring GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini in ChatGPT” “Claude 4.5 just works and it's crazy good.”
Comment from 22 Nov 2025 in “AI is a front for consolidation of resources and power” “Claude has better tooling and UX.”
Comment from 22 Dec 2025 in “GLM-4.7: Advancing the Coding Capability” Understands what users want
“they do exactly what I tell them to most of the time”
Comment from 30 Dec 2025 in “The 70% AI productivity myth: why most companies aren't seeing the gains” “4.5 would make sure it understands what I want”
Comment from 7 Apr 2026 in “Claude Code is unusable for complex engineering tasks with the Feb updates”
What people warn about
Each mark is one comment
Makes frequent mistakes and hallucinations
“The context grows very quickly and the LLM gets lost and starts hallucinating.”
Comment from 7 Feb 2026 in “Evaluating and mitigating the growing risk of LLM-discovered 0-days” “It makes mistakes every day.”
Comment from 20 Dec 2025 in “Ask HN: Are you afraid of AI making you unemployable within the next few years?” Reverts fixes and rewrites model calls
“will often just randomly rewrite calls to GPT5 to GPT4o, or Claude 4.5 to Claude 3.5”
Comment from 20 Nov 2025 in “Building more with GPT-5.1-Codex-Max” “Claude 4.5 often starts reverting bug fixes ~50k tokens back”
Comment from 5 Feb 2026 in “Claude Opus 4.6” Overly agreeable, sycophantic replies
“Even Claude 4.5 models are still somewhat prone to "You're absolutely right!"”
Comment from 12 Dec 2025 in “GPT-5.2” “Of course they did, they are sycophants”
Comment from 1 Dec 2025 in “Show HN: ER Intern Simulator Built in 3 Hours via Natural Language Rules”
Other language models people recommend
The four most recommended other language models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Claude Opus | 3,331 | 2,746 | 55% | 13 | 4 mo156 owners | — |
| OpenAI GPT | 1,205 | 987 | 55% | 13 | 6 mo47 owners | — |
| Claude Sonnet | 854 | 586 | 59% | 13 | 6 mo46 owners | — |
| DeepSeek V4 Flash | 828 | 223 | 79% | 8 | 1 mo24 owners | Approved |
| Claude 4.5 (Anthropic)This page | 32 | 11 | 74% | 11 | — | Approved |
What people said
40 of the 44 comments that mention it, newest first. Each links to the original comment.
“very easily readable, enjoyable plain-ascii-text, with no Ai-ick”
“It went from frequent hallucinations to highly usable with much less garbage output.”
“so was 4.5 BUT as long as we steer it IT does a good enough job”
“I've been satisfied with the results I get using 4.5”
“has/had an obsession with the number 47 (or number containing 47)”
“4.5 was a monster, 4.6 a clear regression, and then 4.5 was dumbed down”
“4.5 would make sure it understands what I want”
“once 4.5 goes away I will have to find another provider”
“they were right about 4.5 and 4.6”
“If there's a model that's as good as Claude 4.5 (not even 4.6) I would pay tens of thousands to run it locally.”
“still wandered, but it could sometimes circle back”
“those models are actually quite useful and powerful”
“4.5 was enough to convince me to adopt for production code.”
“not at the level of what Cloud released with 4.5”
“I also feel like 4.5 was just way more efficient too”
“The context grows very quickly and the LLM gets lost and starts hallucinating.”
“Claude 4.5 often starts reverting bug fixes ~50k tokens back”
“Much better feel with the Claude 4.5 series, for both chat and coding.”
“Why Gemini over GPT-5/Claude4.5 for agent orchestration”
“There are tasks that you'd have to reroll 3.5 til the end of the universe that 4.5 would one shot.”
“Claude 4.5 is by far the best/fastest coding model”
“Speaking of either Claude Code as a tool, or Claude 4.5 as an LLM used with coding.”
“they do exactly what I tell them to most of the time”
“I still can’t trust any of the things to work on any modestly complex codebase without close supervision”
“for many many tasks there is not significant improvement”
“Claude has better tooling and UX.”
“It tends to produce very good, clean, well-documented code and tests.”
“It makes mistakes every day.”
“The fix was to just switch to Claude 3.5 and now to 4.5 in VSCode.”
“Even Claude 4.5 models are still somewhat prone to "You're absolutely right!"”
“Claude 4.5 has a ridiculous amount of knowledge”
“Of course they did, they are sycophants”
“For the work I am doing, I found Claude 4.5 (both models) to be absolutely unchallenged.”
“Claude 4.5 and Codex have replaced my sed/search and replaces, write my sanity tests, write my commit comment”
“Claude 4.5 just works and it's crazy good.”
“doesn't feel as good as Claude 4.5”
“claude 4.5 has not changed a thing on how we work”
“claude 4.5 is changing how I work”
“will often just randomly rewrite calls to GPT5 to GPT4o, or Claude 4.5 to Claude 3.5”
“it is pretty incredible that GPT 5 and Claude 4.5 can perform at this level already”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.