Benchmarking models across effort levels and harnesses on eval suites with real coding tasks. Because you don't need High or Max effort as much as you think.
Another week, another eval suite. This is a very special week since we are beginning work on our first language-specific eval suite.
And the first language we'll be focusing on is OCaml đĢ
We picked OCaml because it's a language that doesn't get a lot of attention in coding benchmarks. It's time to give this amazing programming language the attention that it deserves.
Coming soon đ