I didn't accept a single edit from this model over the entire week, just saying. I do not understand how it's being benchmarked on par with Sol and other larger models.
I didn't accept a single edit from this model over the entire week, just saying. I do not understand how it's being benchmarked on par with Sol and other larger models.
It was certainly almost RL-fried to overfit the benchmarks, at the expense of actual usability. See Opus 5.
is it a benchmarkmaxxing model?!