But I do care about capability and so far only Anthropic and, very recently with Astra, OpenAI can deliver on coding quality. And capability matters immensely. There is a world of difference between being able to do something and not being able.
It's definitely a lot slower, though
There are things GPT 6.0 can accomplish for me that 5.3 was not able to. But there are also things it still fails at, and it doesn't seem to be much better at the big picture. It does spam about 100x more tests though and I wonder if just RLHFing it to test everything constantly is carrying it more. 6.0 writes so many tests and spends so much time verifying it's work in python sandboxes. Slow as hell but it tends to get things right the first time more which is good, I guess. I don't love the thought of a 500loc feature adding +4000loc due to tests though.
And yeah still for some reason they often can't understand how to set up any project locally without handholding, which is something you'd think an LLM would actually be good at
AFAIK: Mistral does not even try to compete in this field. There are other use cases for LLMs beside coding. As Mistral AI wrote:
> During the first wave of generative AI, the central question was who could build the most powerful model. Organizations and governments are now asking a different one: how to harness the power of AI for their mission-critical needs without surrendering control over the infrastructure and intelligence loop. Demand for that combination of performance with control, choice and independence is growing internationally, as enterprises and governments weigh the long-term technology dependencies, data governance requirements and deployment choices that come with any AI investment.
> Mistral is the only AI company in the world building the full stack required to answer that question: open-weight models, the infrastructure and the compute capacity they run on, and the products that bring them into production; ensuring that customers are never locked into a single vendor's roadmap, pricing or availability.
> Mistral’s full-stack and open approach also allows organizations to build on it without exposing their most valuable data, workflows and institutional knowledge to anyone outside their own walls. That's what makes Mistral’s stack the sovereign AI layer, meaning retaining control across four dimensions: data that stays inside the organization's boundaries, models that are controllable and customizable, compute that is private and predictable, and systems in production that are fully controllable and auditable.
They have released models speficially for programming that ”vibe coding” would be safer.
Even those old llama models were ok for coding
Yes yes they won't be like Claude's fire and forget (until you see how many tokens you burned to write "Hello World")
Saying only anthropic models are competitive frontier coding models is out of touch with the space imo
You must care about good benchmarks (identify those that have relevance).
If I read forums and talk to people IRL most have differing opinions what model is best. Yes, for me it's pretty clear Opus is better than earlier models, but it's at least not obvious to me that the later are significant improvements.
It can be subjective, at this stage of product availability.
Personally, I hate to be frustrated by gross intellectual faults, so I did some research in the past about the best benchmarks to assess pure (simulated, apparent) intelligence. (The quality of the found benchmarks may not reflect what the models seem to do in practice, so one's experience should be compared to the raw numbers out of the benchmarks.) Good ideas emerge in the field: it was proposed and discussed on these very pages that the LLM should be able to solve "murder mysteries", for example (alongside the pattern recognition problems in which IQ tests consist, etc.).
Moreover, the LLM shall not delirate. It is an intrinsic issue with the current architectures (they do not mirror the "Foundational theory of Knowledge", which requires confidence values and relations of foundation between notions), but it is a problem with more or less presence per model. Artificial Analysis has introduced a metric for that.
Moreover again, I want an output style that works well for the purpose - must not be a clashing style like "youngspeak" ("like, awsome") or "paternalistspeak" ("when a planet likes another very much they are attracted...") or "sycophantspeak" ("your question is so deep and interesting") or "wetspeak" ("you can do it, feel this not that")... So, for example, I very much preferred Kimi k2 to gpt-oss-120b. I doubt there are benchmarks for this - "seriousspeak", "maturespeak" - but there should be.