[–] bytefactory 2y ago ↗ WizardLM claims to have beaten GPT4 on HumanEval with 73.2% @ Pass1 to GPT4s 67% (in the original GPT4 report).Big, if true. Their own testing puts present GPT4 at 82%, but 73.2% still seems very competitive.
1 comment
[ 3.5 ms ] story [ 13.4 ms ] threadBig, if true. Their own testing puts present GPT4 at 82%, but 73.2% still seems very competitive.