On livebench.ai, GPT-5 is the best model overall, and the second best for agentic coding. But for the Coding benchmarks, it's ranked like 20th. Quite interesting. I'm finding it exceptional for non-trivial summarization tasks.
> So you upload a .jsonl file with the above JSON, and then you try to submit it for a batch job. If something is wrong with your file, you'll get a "400" and no other info. If something is wrong with the request submission you'll get a 400 with "Invalid JSON payload received. Unknown name \"file_name\" at 'batch.input_config.requests': Cannot find field."
Thanks for your post, I've stumbled upon the same issue as you.
So I should interpret the "Unknown name \"file_name\" at 'batch.input_config.requests'" as an error with the jsonl file and not the payload itself?
I'm trying to submit a batch with a .jsonl file, but I'm always getting the "Unknown name \"file_name\" at 'batch.input_config.requests'" error.
Reading file line by line may seem like a trivial problem, but in node, there is no straightforward way to do it. There are a lot of libraries using Transform Streams to achieve it, but it seems like a overkill, so I've wrote simple version using only the filesystem module of node.
Also it's a lot slower than Claude and Google models.
In general GPT models doesn't work well for me for both coding and general questions.