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.
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.
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.
https://gist.github.com/drorm/7851e6ee84a263c8bad743b037fb7a...
I typically use github issues as the unit of work, so that's part of my instruction.
The way "Phases" are handled is incredible with research then planning, then execution and no context rot because behind the scenes everything is being saved in a State.md file...
I'm on Phase 41 of my own project and the reliability and almost absence of any error is amazing. Investigate and see if its a fit for you. The PAL MCP you can setup to have Gemini with its large context review what Claude codes.
Every new model overfits to the latest overhyped benchmark.
Someone should take this to a logical extreme and train a tiny model that scores better on a specific benchmark.
It's not just over-fitting to leading benchmarks, there's also too many degrees of freedom in how a model is tested (harness, etc). Until there's standardized documentation enabling independent replication, it's all just benchmarketing .
But even an imperfect yardstick is better than no yardstick at all. You’ve just got to remember to maintain a healthy level of skepticism is all.
When such benchmarks aren’t available what you often get instead is teams creating their own benchmark datasets and then testing both their and existing models’ performance against it. Which is eve worse because they probably still the rest multiple times (there’s simply no way to hold others accountable on this front), but on top of that they often hyperparameter tune their own model for the dataset but reuse previously published hyperparameters for the other models. Which gives them an unfair advantage because those hyperparameters were tuned to a doffeeent dataset and may not have even been optimizing for the same task.
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.
Cost to Run Artificial Analysis Intelligence Index:
GPT-5.2 Codex (xhigh): $3244
Claude Opus 4.5-reasoning: $1485
(and probably similar values for the newer models?)
Not throwing shade anyone's way. I actually do prefer Claude for webdev (even if it does cringe things like generate custom CSS on every page) -- because I hate webdev and Claude designs are always better looking.
But the meat of my code is backend and "hard" and for that Codex is always better, not even a competition. In that domain, I want accuracy and not speed.
Solution, use both as needed!
This is the way. People are unfortunately starting to divide themselves into camps on this — it’s human nature we’re tribal - but we should try to avoid turning this into a Yankees Redsox.
Both companies are producing incredible models and I’m glad they have strengths because if you use them both where appropriate it means you have more coverage for important work.
Ah and let me guess all your frontends look like cookie cutter versions of this: https://openclaw.dog/
(I'm also a "small steps under guidance" user rather than a "fire and forget" user, so maybe that plays into it too).
It's a very nice UX for iteratively creating a spec that I can refine.
Opus is the first model I can trust to just do things, and do them right, at least small things. For larger/more complex things I have to keep either model on extremely short leashes. But the difference is enough that I canceled my GPT Pro sub so I could switch to Claude. Maybe 5.3 will change things, but I also cannot continue to ethically support Sam Altman's business.
All that said, the single biggest reason why I use Codex a lot more is because the $200 plan for it is so much more generous. With Claude, I very quickly burn through the quota and then have to wait for several days or else buy more credit. With Codex, running in High reasoning mode as standard with occasional use of XHigh to write specs or debug gnarly issues, and having agents run almost around the clock in the background, I have hit the limit exactly once so far.
Hopefully performance will pick up after the rollout.
As an analogy, Terence Tao may be one of the smartest people alive now, but IQ alone isn’t enough to do a job with no domain-specific training.
The only valid ARC AGI results are from tests done by the ARC AGI non-profit using an unreleased private set. I believe lab-conducted ARC AGI tests must be on public sets and taken on a 'scout's honor' basis that the lab self-administered the test correctly, didn't cheat or accidentally have public ARC AGI test data slip into their training data. IIRC, some time ago there was an issue when OpenAI published ARC AGI 1 test results on a new model's release which the ARC AGI non-profit was unable to replicate on a private set some weeks later (to be fair, I don't know if these issues were resolved). Edit to Add: Summary of what happened: https://grok.com/share/c2hhcmQtMw_66c34055-740f-43a3-a63c-4b...
I have no expertise to verify how training-resistant ARC AGI is in practice but I've read a couple of their papers and was impressed by how deeply they're thinking through these challenges. They're clearly trying to be a unique test which evaluates aspects of 'human-like' intelligence other tests don't. It's also not a specific coding test and I don't know how directly ARC AGI scores map to coding ability.
Not very accurate. For each of ARC-AGI-1 and ARC-AGI-2 there is training set and three eval sets: public, semi-private, and private. The ARC foundation runs frontier LLMs on the semi-private set, and the labs give them pre-release API access so they can report release-day evals. They mostly don't allow anyone else to access the semi-private set (except for live Kaggle leaderboards which use it), so you see independent researchers report on the public eval set instead, often very dubious. The private is for Kaggle competitions only, no frontier LLMs evals are possible.
(ARC-AGI-1 results are now largely useless because most of its eval tasks became the ARC-2 training set. However some labs have said they don't train LLMs on the training sets anyway.)