[ezoe]

While the tread is swapping between "OMG Claude good. OpenAI was done for" and "OMG Codex good. Anthropic was done for". I've never heard about Gemini and Grok. It works mostly similar performance, but people don't mention that much.

Still, my impression is, Gemini hallucinate too much while Grok is always less capable than competitors so it's not worth using it.

[margalabargala]

Gemini is the best model for OCR bar none.

It absolutely sucks at coding.

[jadbox]

I get great results when operating at just a 'file' level. It's not so great at editing across many files.

[Auracle]

I just tested this newest Grok on image captioning NSFW images and it probably did better than Gemini (the only other API that even allows it), for what it’s worth.

[kardianos]

Gemini 2.5 and 3 can code, but they are also dumb. They don't model the world well. It's hard to use them for programming tasks.

I haven't tried grok4.2 or grok4.3 yet for coding, but it wasn't up to the challenge as an agent yet. It looks like grok4.3 shifted its training and operates always as an agent first judging on some web usage. Musk knows grok is behind and states it publically. Now with grok4.3 release I do plan to try it again to see if it is suitable.

[WarmWash]

Gemini weakness is coding, but it will go toe to toe with 5.5 for science, (classic) engineering, finance, basically not programming stuff. It also does it while using about 1/4 the tokens.