As a happy OpenRouter user I know the vast majority of the industry directly use vendor APIs and that the OpenRouter rankings are useless for those models.
I use codex high because Anthropic CC max plan started fucking people over who want to use opus. Sonnet kind of stinks on more complex problems that opus can crush, but they want to force sonnet usage and maybe they want to save costs.
Codex 5 high does a great job for the advanced use cases I throw at it and gives me generous usage.
Well that may also be because ChatGPT is worse than Gemini and Claude for coding. I don't know what the benchmarks say, I am just saying that from my own experience.
As a happy OpenRouter user I know the vast majority of the industry directly use vendor APIs and that the OpenRouter rankings are useless for those models.
OpenRouter probably doesn't mean much given that you can use the OpenAI API directly with the openai library that people use for OpenRouter too.
OpenAI is BYOK-only on OpenRouter, which artificially depresses its utilization there.
I use codex high because Anthropic CC max plan started fucking people over who want to use opus. Sonnet kind of stinks on more complex problems that opus can crush, but they want to force sonnet usage and maybe they want to save costs.
Codex 5 high does a great job for the advanced use cases I throw at it and gives me generous usage.
Well that may also be because ChatGPT is worse than Gemini and Claude for coding. I don't know what the benchmarks say, I am just saying that from my own experience.