GPT-5.3-Codex • Hacker News Board

Re: GPT-5.3-Codex

#61

Post by wasmainiac » Thu, Feb 05, 2026, 6:41 PM UTC

raincole wrote: post #33

rishabhaiover wrote: post #27

Earlier quoted context omitted.

What happened to you?

AI fried brains, unfortunately.

I mean, he has a point it’s just not very eloquently written.

Re: GPT-5.3-Codex

#62

Post by wahnfrieden » Thu, Feb 05, 2026, 6:42 PM UTC

Pelican seems much worse than the Opus 4.6 one (though the bicycle is more accurate):

https://gist.github.com/simonw/a6806ce41b4c721e240a4548ecdbe...

Re: GPT-5.3-Codex

#63

Post by aurareturn » Thu, Feb 05, 2026, 6:42 PM UTC

the_duke wrote: post #19

granzymes wrote: post #3

I think Anthropic rushed out the release before 10am this morning to avoid having to put in comparisons to GPT-5.3-codex! The new Opus 4.6 scores 65.4 on Terminal-Bench 2.0, up from 64.7 from GPT-5.2-codex. GPT-5.3-codex scores 77.3.

I do not trust the AI benchmarks much, they often do not line up with my experience. That said ... I do think Codex 5.2 was the best coding model for more complex tasks, albeit quite slow. So very much looking forward to trying out 5.3.

5.2 Codex became my default coding model. It “feels” smarter than Opus 4.5.

I use 5.2 Codex for the entire task, then ask Opus 4.5 at the end to double check the work. It's nice to have another frontier model's opinion and ask it to spot any potential issues.

Looking forward to trying 5.3.

Re: GPT-5.3-Codex

#64

Post by maxpert » Thu, Feb 05, 2026, 6:42 PM UTC

kingstnap wrote: post #10

That was fast! I really do wonder whats the chain here. Did Sam see the Opus announcement and DM someone a minute later?

Tell me that you are hurt without telling me that you are hurt this applies to Sam right now

Re: GPT-5.3-Codex

#65

Post by modeless » Thu, Feb 05, 2026, 6:42 PM UTC

input_sh wrote: post #53

modeless wrote: post #41

It's so difficult to compare these models because they're not running the same set of evals. I think literally the only eval variant that was reported for both Opus 4.6 and GPT-5.3-Codex is Terminal-Bench 2.0, with Opus 4.6 at 65.4% and GPT-5.3-Codex at 77.3%. None of the other evals were identical, so the numbers for them are not comparable.

It's better on a benchmark I've never heard of!? That is groundbreaking, I'm switching immediately!

I also wasn't that familiar with it, but the Opus 4.6 announcement leaned pretty heavily on the TerminalBench 2.0 score to quantify how much of an improvement it was for coding, so it looks pretty bad for Anthropic that OpenAI beat them on that specific benchmark so soundly.

Looking at the Opus model card I see that they also have by far the highest score for a single model on ARC-AGI-2. I wonder why they didn't advertise that.

Re: GPT-5.3-Codex

#66

Post by hoeoek » Thu, Feb 05, 2026, 6:43 PM UTC

DonHopkins wrote: post #25

zozbot234 wrote: post #12

Earlier quoted context omitted.

They're also coordinating around Chinese New Year to compete with new releases of the major open/local models.

Year of the Pelican!

simonw?

Re: GPT-5.3-Codex

#67

Post by rs_rs_rs_rs_rs » Thu, Feb 05, 2026, 6:43 PM UTC

edem wrote: post #23

So can I use this from Opencode? Because Anthropic started to enforce their TOS to kill the Opencode integration

You can use Anthropic models in Opencode, make an api key and you're good to do(you can even use the in house Opencode router, Zen).

What you can't do is pretend opencode is claude code to make use of that specific claude code subscription.

Re: GPT-5.3-Codex

#68

Post by esafak » Thu, Feb 05, 2026, 6:43 PM UTC

kingstnap wrote: post #29

uh_uh wrote: post #24

Earlier quoted context omitted.

How so?

Its kind of a suck up that more or less confirms the beef stories that were floating around this past week. In case you missed it. For example: Nvidia's $100 billion OpenAI deal has seemingly vanished - Ars Technica https://arstechnica.com/information-technology/2026/02/five-... Specifically this paragraph is what I find hilarious. > According to the report, the issue became apparent in OpenAI’s Codex, an AI code-gen…

> OpenAI staff reportedly attributed some of Codex’s performance limitations to Nvidia’s GPU-based hardware.

They should design their own hardware, then. Somehow the other companies seem to be able to produce fast-enough models.

Re: GPT-5.3-Codex

#69

Post by morleytj » Thu, Feb 05, 2026, 6:44 PM UTC

The behind the scenes on deciding when to release these models has got to be pretty insanely stressful if they're coming out within 30 minutes-ish of each other.

Re: GPT-5.3-Codex

#70

Post by koakuma-chan » Thu, Feb 05, 2026, 6:44 PM UTC

aurareturn wrote: post #63

the_duke wrote: post #19

Earlier quoted context omitted.

I do not trust the AI benchmarks much, they often do not line up with my experience. That said ... I do think Codex 5.2 was the best coding model for more complex tasks, albeit quite slow. So very much looking forward to trying out 5.3.

5.2 Codex became my default coding model. It “feels” smarter than Opus 4.5. I use 5.2 Codex for the entire task, then ask Opus 4.5 at the end to double check the work. It's nice to have another frontier model's opinion and ask it to spot any potential issues. Looking forward to trying 5.3.

Opus 4.5 is more creative and better at making UIs