Grok 4.7

195

mmeetpateltech about 2 hours ago 136 commentsRead Article on x.ai

DE version is available. Content is displayed in original English for accuracy.

⚡ Community Insights

Discussion Sentiment

76% Positive

Analyzed from 2775 words in the discussion.

Discussion (136 Comments)Read Original on HackerNews

moojacob•about 2 hours ago

Apparently Grok 4.7 has 40% more weights than Grok 4.6, but the price ($6 output token, $2 input) is the same.

Given that the decrease in their margin and the fact they delayed the release of Grok 4.7 almost two weeks past the original date, XAI must not have been happy with the results for 4.7. And XAI also waited the day before Opus 5.5 is rumored to launch. I imagine Opus 5.5 will blow Grok 4.7 out of the water benchmark wise.

However, I have become skeptical of benchmarks. Grok 4.5 solved some issues setting up a buildroot system that Fable 5 couldn't do. I find the post cursor groks are phenomenal at frontend web development, though Claude is much better at backend ruby.

My favorite part of the new Groks has been how they speak in plain english. I simply cannot stand Claudish. Or even GPT, which doesn't have Claude's ticks but definitely likes to handwave explaining technical concepts. Still, nothing beats Claude 3.5 and 4 with explaining since it seems all models have regressed. I wonder if Grok 4.7 will also regress with English because of all the RL.

smashers1114•24 minutes ago

FYI a quick fix for claudish is to ask for the response to be in ASD-STE100 (Simple Technical English). Then it is far more readable. But I would agree that this is an annoyance and shouldn't require user workaround to get something readable.

snapplebobapple•13 minutes ago

This fixed claude! Thanks!

_boffin_•18 minutes ago

Does not work for Claude, at least for me and I put it as the system prompt

Lucasoato•about 1 hour ago

> I simply cannot stand Claudish

I totally agree, it’s like that as models become more intelligent, they are less understandable by most of people... but aren’t we humans doing the same?

TomGarden•38 minutes ago

Agreed. The more knowledge you amass on a subject, the more important it becomes to be extremely specific and nuanced - or your communications end up being incorrect. You become better at expressing your thoughts, but harder to understand.

The weird thing is, that's not what AI models seem to be doing. The prose is just weird.

unshavedyak•30 minutes ago

> You become better at expressing your thoughts, but harder to understand.

This happens most though when the speaker doesn't (or care to) understand their audience.

Eg i find effective communication requires expertise in both the subject matter domain but also the reference of the listener. Eg in ELI5 framing, if you don't know what information 5yr olds are expected to know you'll do a poor job at an ELI5.

It often feels like Claude does poorly at both framing the response relative to what it "thinks" the listener knows, but also the prose is... sideways, just weird as you said.

Aperocky•about 1 hour ago

The best ideas are usually the simplest to elaborate. If someone comes up with a convoluted scheme that are hard to understand or be adequately explained, it's usually fraud.

When claude speak in convoluted mess, they are often going off on tangents in real work that you asked it to do, too.

fragmede•about 1 hour ago

That believes that the world can be simplified into dichotomies, or at least, simplified. Sometimes problems are complex, and the solutions to them necessarily so. For example, cancer. I order to begin to understand that problem, you have to understand the utter complex scheme it has devised in order to exist. A 20 minute YouTube video isn't going to be able to begin to cover the basics of the subject, although there are some good ones, with clever analogies.

Just because something is difficult to understand doesn't mean it's fraud, although if someone is trying to dazzle you with clever words and names of institutions you recognize because they are selling you something, there's a good chance they're lying to you in order to get some money from you.

samuelknight•about 1 hour ago

That's half true. A very smart model should be able make good explanations, which include simple understandable prose. That can should be possible even as its thought process gets more alien.

superjan•37 minutes ago

What I notice about Claudish is that it has its preferred cliche’s and overstretched methaphores, it packs too many ideas in a sentence, and to achieve the latter it makes up adjectives.

I should try adding these tips to my system prompt. Is there a shorthand to describe such language use? I am not a native English speaker.

svachalek•6 minutes ago

Look up the output-style setting, which is a bit stronger than putting it in the system prompt. The new "concise" setting is better than the default but in practice, Claude is a very stubborn model when it comes to these patterns and they're really hard to eliminate, mostly you can only hope to mitigate.

As for the wording of the prompt, you're pretty on point, I created a custom output style targeting mostly the first two you have there. Some people have wording that demands a certain technical standard or uses fancy words to describe what to avoid, but I haven't seen evidence those work better than asking plainly and I suspect the opposite: LLMs mimic the user to a degree so talking to it in terms of technical specifications and fancy words is an invitation to get them back.

grababner•about 1 hour ago

If you can't explain it simply, you don't understand it well enough

jasonjmcghee•about 1 hour ago

For what it's worth - over the last few years or whatever, it seems like Anthropic benchmaxxes the least.

That being said, I currently prefer Sol / Astra to Opus / Fable as I find both to be a better cost payoff to me.

vessenes•about 1 hour ago

I was going to say the reverse - claude has been the less satisfying normalized by benchmark for me in the last year. Both astra and fable have their quirks, but I am 90% codex this year up from 10% last year.

vintermann•20 minutes ago

It's not just about benchmaxxing. Sincerely targeting those long-autonomy benchmarks is questionable in the first place, because naturally it drives the model to assume more and more about what you want.

svachalek•3 minutes ago

The target market for frontier models is CEOs who want to lay off entire departments of their company. So the long autonomy benchmarks would seem to be sending exactly the right signal.

tk90•10 minutes ago

> I find the post cursor groks are phenomenal at frontend web development, though Claude is much better at backend ruby.

Wonder if we'd benefit from a much more specialized + task-specific benchmarks to paint a clearer picture like this. A benchmark solely for frontend, ruby, hardware, etc.

dmix•7 minutes ago

Agreed, Claude has a "Claude Design" tool but doesn't publish any frontend brenchmarks. Maybe the industry will develop one.

algoth1•6 minutes ago

I've noticed Chatgpt 5.6 Sol High, on the chat interface, inventing words that are a mixture of Portuguese and English. Like "hardcodar" a mix of "hardcode" and the most common verb ending in Portuguese "-ar". Some don't have a single google hit

rayiner•6 minutes ago

> My favorite part of the new Groks has been how they speak in plain english.

I don't know if it's the plain english or what, but I really like Grok for legal research (as opposed to code). It's got a noticeable edge in getting to the point compared to Opus 5.

WarmWash•40 minutes ago

Perhaps you haven't had the chance to use it, but 3.8 flash is the best model for talking too. Even routing Claudes output through 3.8 to have it explain whats going on is a breath of fresh air

svachalek•2 minutes ago

Agreed. It's very capable for something carrying the "flash" label, super fast, and very clear to read.

esafak•16 minutes ago

I would if they let me bring the subscription I have to the harness of my choice.

AustinDev•38 minutes ago

gemini 3.8 flash?

jtwaleson•22 minutes ago

yes

dumberquestions•about 1 hour ago

Token price doesn't tell you much without knowing token efficiency.

user43928•about 1 hour ago

Their leading benchmark with cost per task shows a tough sell compared to Fable 5.1 Low and doesn't reach the performance of Fable 5.1 Medium.

How representative that is of real world usage, I don't know.

In their benchmark GPT 5.6 Sol performs suspiciously poorly compared to the former models.

Waterluvian•22 minutes ago

Using a variety of models feels similar to the benefit of having a team of individuals from different backgrounds.

atniomn•about 1 hour ago

I expect the next Anthropic release to finally reduce the prevalence of Claudish

moojacob•about 1 hour ago

If they fix Claudish, they've earned me back as a max customer!

Fable 5.1 is not there quite there yet.

They need to get that Sonnet 3.5 magic back.

rfgplk•39 minutes ago

Same. The issue with Anthropics models is that (speaking regarding code generation) they REFUSE any kind of comment override instructions. I've tried everything and no matter what, after a few turns, they resort to generating the same overtly verbose junk. Bun's codebase is littered with them See

   // `HANDLE` is an opaque kernel handle (kernel32 validates and returns 0/FALSE
   // on a non-console handle); every out-param is `&mut T` to a `#[repr(C)]` POD,
   // ABI-identical to the Win32 `LP*` pointer (thin non-null). The reference type
   // encodes the only pointer-validity precondition, so `safe fn` discharges the
   // link-time proof. (`bun_windows_sys::kernel32` declares these with `*mut`;
   // redeclared locally so the legacy-conhost cursor path below is plain calls.)

   // Progress's terminal handle is the canonical `output::File` (vtable-backed
   // stderr/File from `OutputSinkVTable`). The duplicate `ProgressTerminalVTable`
   // from B-0 round 1 is removed; tty/ansi/winsize route through    the new
   // `OutputSinkVTable` slots so `bun_core` stays T0 (no `bun_sys` dep).

from src/bun_core/Progress.rs

sscaryterry•about 1 hour ago

Based on?

7734128•33 minutes ago

It's pretty much the biggest complaint of Claude compared to its competitors, so they really should adress it .

xmorse•39 minutes ago

it's definitely not bigger. smaller if anything looking at how much faster it is

vessenes•about 1 hour ago

Nice to see this release cadence increasing and some continued improvement in quality. I am guessing these models are basically still outcomes of the cursor team integrating with the massive amount of compute they now own: I’d imagine we will see significant step up improvements with grok 5 later this year as the team gets more experienced and confident with larger training deployments. Here’s hoping for another competitive frontier model!

simonw•35 minutes ago

https://tools.simonwillison.net/markdown-svg-renderer?url=ht... - default reasoning level.

Here's reasoning level high: https://tools.simonwillison.net/markdown-svg-renderer?url=ht...

For some reason reasoning effort low and medium used similar numbers of tokens, and xhigh used less than high. I think I need to try without OpenRouter in the middle.

datsci_est_2015•4 minutes ago

Poor fella doesn’t have a seat. Intriguing design where both pedals are on the same side of the frame. Balancing must be a challenge.

MattDamonSpace•13 minutes ago

Are there good tools for doing context audits? I feel I have no good way to visualize what a new session is getting by default in a given repo without crawling through every potentially included markdown file

swalsh•14 minutes ago

Codex has become my goto tooling. I used to be a Claude Max subscriber, but I was becoming disappointed with the quality of the output from Opus 5. Fable chewed through my usage too quickly to be practical. Moving to a Pro account w/ Codex was a big improvement. Sol had great output, and the usage was more than sufficient for most of my needs. However astra does tend to chew up usage, so when i've done to much of that, and it's became an issue Grok Build has beocme my second go to account. The output especially after the cursor purhcase has become quite good, and the usage has always been very generous.

saejox•38 minutes ago

Not even close to astra. Astra is something else. It is expensive, but uses way fewer tokens do my tasks.

xAI missed its chance, Ball is on Anthropic's court.

redox99•4 minutes ago

Not surprising considering Grok 4.7 is a 2T model, so Sol/Opus class, not Astra/Fable class.

enraged_camel•10 minutes ago

Astra fails in similar ways, and at similar frequency, as GPT 5.6 Sol does. It often goes way out of scope, or just stops prematurely, or tries to find odd and even dangerous workarounds when it gets stuck.

It's phenomenal at computer use and 3D stuff. I've been using it less and less for coding.

WarmWash•42 minutes ago

Good thing they used 5.6 sol instead of Astra for benchmarks, the EEbench one is crazy[1]

[1]https://eebench.org/

simonw•about 1 hour ago

$2/million inout and $6/million output but I couldn't see any pricing information for cached input tokens?

sejje•28 minutes ago

cached input tokens are $0.50 per 1M (prompts under 200k tokens) and $1.00 per 1M (200k+)

simonw•5 minutes ago

Do other prices vary for >200,000 or just the cached tokens?

btian•27 minutes ago

$0.40

AM1010101•about 1 hour ago

Did 4.6 not have an x-high reasoning level? Why are they comparing 4.7 x-high with 4.6 high?

ssutch3•38 minutes ago

It did not. xhigh is new to grok.

forgot-my-pw•32 minutes ago

Not sure on the API side, in Cursor you can always use 4.6 at xhigh.

ssutch3•12 minutes ago

We've only used it through API - but you're right, now API supports xhigh for 4.5-4.7.

maz1b•about 1 hour ago

Either way, the fact that xAI or SpaceXAI or whatever the name is, I can commend the team behind it on their rapid ascent and progress by being close and or on the frontier in several respects.

avazhi•33 minutes ago

Your comment is like 6 months to a year late.

There for awhile it seemed like we’d have 3 big competitors but then Grok 4.2 or 4.4 was just diabolical while OAI and Claude continued their significant improvements. Grok was/is so bad that I was convinced musk was gonna shut it down and just fund Anthropic compute once they reached their compute agreement.

6thbit•about 1 hour ago

( why is the x-axis on the first chart in descending order ? )

meerita•about 1 hour ago

Grok it's really expensive. I'm getting really amazing results using DeepSeek 4.1 Flash for fraction of the price.

testfrequency•41 minutes ago

What is the most secure way to use this model as someone who is lazy

user43928•24 minutes ago

I understand DeepSeek 4.1 Flash is available on US providers with Zero Data Retention if that is what you are asking.

parineum•about 1 hour ago

Brought to you by...

meerita•about 1 hour ago

By no one. For the price of 1M token you can get more and with better results with other models.

MuffinFlavored•42 minutes ago

If the CursorBench 4.0 score diagram is the headline, I read it as "Grok 4.7 xHigh is almost the same as Fable5.1 on low".

Is there a metric for like... time taken when comparing these two? I see score and cost.

If Fable5.1 can knock it out more quickly on low but Grok4.7 might take twice as long to stumble through a problem (and leave behind a bunch of yucky comments or un-needed extra unit tests), are they really comparable?

Or like... the "quality" of the solution? "It works" versus "it's unmaintainable/very messy/hacky".

ls1911•about 2 hours ago

after using cursor grok & trae.ai for several months , grok curor is highly superior results to trae.ai

Saline9515•about 1 hour ago

I tried in Omp (Oh-my-pi), and so far it's really problematic.

It will loop in thinking mode ("Let me implement those fixes: Fix 1, Fix 2, Fix 3 .... Fix 80, Fix 81"), ignore the AGENTS.md instructions, corrupt plan files, etc etc... I have 5.6 Sol as advisor/watchdog, and it blocks every turn, I never saw this. Quite a shame, 4.6 wasn't so bad.

xmorse•38 minutes ago

OMP is a joke. don't use that garbage

polytely•10 minutes ago

what do you use and why do you prefer it over omp

unrvl22•16 minutes ago

you are a joke if you think omp is a joke.

Saline9515•26 minutes ago

Can you explain your opinion? I'm curious but such vague comments won't convince me.

samtheprogram•9 minutes ago

Probably the same reason as oh-my-zsh, you don't need 90% of it. Further compounding the problem in an agent harness is that you are polluting the context window by throwing the kitchen sink at it.

sidgtm•about 1 hour ago

In my experience Grok especially inside Grok build is pretty solid choice, it’s a no nonsense model and stays on its course. Another surface where I truly enjoy the experience of using Grok model is Grok bot

guywithahat•28 minutes ago

I've had really good experiences with Grok 4.6 and grok build. I've been playing around with tscircuit and it can write code with an understanding of spacial reasoning, while also importing cad components from different file formats into tsx, I've been having claude come in and try to error check it and so far claude hasn't found anything to improve in my three projects.

I'm excited for 4.7 although I share skepticism with other users whether 4.7 will be significantly better, since they didn't raise the price.

andsoitis•about 1 hour ago

Congratulations to the team!

simianwords•about 2 hours ago

I guess it’s only my opinion but having used grok for personal chat: it’s by far the worst one amongst Claude, ChatGPT and even Deepseek, Gemini etc.

The personality is bland and it doesn’t work nearly as hard or even tries to help.

ethagnawl•7 minutes ago

> it doesn’t work nearly as hard

Until you ask it to start generating horrific imagery and then it's best in class.

slowin•about 1 hour ago

This has been my experience as well. Grok will end tasks almost immediately and claim "Done!". It's definitely the laziest and most "dishonest" of all the models. The others aren't perfect, but I can't use Grok for any serious coding task.

Capricorn2481•about 1 hour ago

> The personality is bland

I don't use Grok, but do you want your LLM to have a personality? "Personality" is exactly what people don't like about Claude.

Razengan•about 1 hour ago

I want my sexbot to have a personality

nython•34 minutes ago

What if it doesn't like you

artemonster•about 1 hour ago

I used openrouter to send same prompt to qwen, derpseek, gemini and grok and found that grok does good research and produces less bullshit, especially when prompted to be critical of an idea

xutopia•about 1 hour ago

Ask it to be critical of the birthday photos and see where that gets you.

artemonster•about 1 hour ago

can you elaborate?

Tsarp•about 1 hour ago

Waiting on simonw "Generate an SVG of a pelican riding a bicycle " benchmark to judge this model

forgot-my-pw•26 minutes ago

It might be more capable, but AA indicates it's a lot less token efficient than Grok 4.6: https://artificialanalysis.ai/agents/coding-agents?agents=co...

kristofferR•about 2 hours ago

What's with the deceptive graph on top? Not including Astra can't have been an oversight, did the model compare poorly to it?

Jcampuzano2•about 1 hour ago

https://openai.com/index/our-decision-on-cursor-following-it...

This explains why. Mentioned in another comment, but cursorbench explicitly tests with Cursor as the harness, and OpenAI doesn't allow them to use Astra in Cursor.

user43928•about 1 hour ago

> with a proposed shutoff date of November 12, 2026

That said, I don't expect them to benchmark Astra in their Cursor harness given the situation.

Jcampuzano2•32 minutes ago

Cursor never added Astra to its consumer subscription plans. And it's likely exactly because of this announcement. Why would they add support for a model they would have to remove shortly after?

kristofferR•about 1 hour ago

That's not accurate. OpenAI doesn't allow Grok to provide Astra to Cursor customers anymore, but it doesn't ban anyone from using Astra via alternative harnesses.

If Cursor wanted to include Astra in CursorBench nothing would stop them, they could easily have spent half an hour vibecoding in OpenAI API key support - if it hadn't been convenient to neglect to do that.

andsoitis•about 1 hour ago

Even if they could do that (workaround to include Astra in CursorBench), that has no practical consequences for Cursor users and that's what I as a Cursor user (what I use for dev, though I use ChatGPT for non-dev stuff) care about.

scottyah•about 1 hour ago

Deceptive? An extremely quick google search would answer your question. OpenAI pulled out of Cursor before they released Astra so it never got that benchmark.

kristofferR•about 1 hour ago

Pulled out from letting them resell Astra access, that's not a limitation on running a benchmark.

Iolaum•about 1 hour ago

I wonder if that means that SpaceX evals show that they consider astra better than fable or that they hate Sam&co so much they don't want to show their stuff.

Jcampuzano2•about 1 hour ago

https://openai.com/index/our-decision-on-cursor-following-it...

Its because of this. You can't use Astra in Cursor, and cursorbench uses cursor as the harness. They can't actually benchmark it using their harness hence why its not included.

ryeguy•39 minutes ago

They can benchmark it because you can use an openai api key with cursor. Astra is just not included in the cursor plan.

babelfish•about 1 hour ago

They have Astra in other benchmarks lower on the page. They just don't want to show it winning

babelfish•about 1 hour ago

this is exactly it.

dom96•32 minutes ago

It’s a shame this model has such negative political baggage associated with it. It’s the only one I decided not to run in my LLM benchmarks[1].

1 - https://bench.killswitch-lang.org

peder•1 minute ago

I think you're seeing a big shift around it.... since it's been markedly cheaper and also still easily available from OpenCode, it's getting large enterprise traction.

sejje•30 minutes ago

You'll have to include it in the future, or your benchmark won't be relevant.

For now, I doubt anyone would notice your protest if you didn't announce it.

zug_zug•about 1 hour ago

Well I "tried it out" I asked it one question, and it gave no answer and said "Sign up to use more!" I don't think I'll be doing that, no.

I can't think of a single dimension grok is winning on (capability, cost, voice), but want to stay open-minded -- anybody want to vouch for its capabilities in any domain?

sejje•38 minutes ago

If you haven't used it, how do you know if it's winning?

I think it's winning on UI for normies (grok bot) and they made some claims about being pareto SOTA (lowest cost per task completed) a while back with 4.6.

I find it to be a perfectly capable model for implementation (there are many in this class--deepseek flash, spark1.3, luna, etc). I find the usage to be very generous w/ supergrok. I find the model to be just fine for 90% of what I want to do, but I use a smarter model to plan complicated things.

swalsh•11 minutes ago

After the cursor aquisition it's become a quite capable coding model. If you take cost into account, it's close to the top. OpenAI is maybe still #1, but I'd put Grok at #2 (again, including cost as a factor).

grim_io•about 1 hour ago

It's probably the most aligned (to a single person) model out there!

puszczyk•42 minutes ago

For me it works well for agentic coding tasks and terminal/unix/bash (in cursor and grok build); it's also token efficient and cheaper than gpt 5.6. It's def not as good as Fable for me (I haven't used Astra much, can't comment). So it's not the cheapest, not the most capable, but it has a good mix of it for my backend, go, infra work.

The voice is the same AI slop as the others imho.

(This is about Grok 4.6, I didn't test 4.7 yet).

edit: clarified I mean agentic coding tasks