Article
🐺🐦⬛ LLM Comparison/Test: 25 SOTA LLMs (including QwQ) through 59 MMLU-Pro CS benchmark runs
wolfram
• • 80
Charles McSneed
ChuckMcSneed
P(doom) <0.001%
AI & ML interests
The name is a subtle joke.
I also do LLM testing for free.
Recent Activity
new activity about 5 hours ago
jukofyork/creative-writing-control-vectors-v3.0:Thulsa Doom liked a model 1 day ago
m-a-p/SheetSage2 liked a model 1 day ago
m-a-p/YuE2-3BOrganizations
upvoted an article almost 2 years ago