Running
Goodharts Law On Benchmarks
⚡
Display benchmark results for language models
Joséphus Cheung
JosephusCheung
AI & ML interests
None yet
Recent Activity
new activity
14 days ago
Qwen/Qwen3-VL-235B-A22B-Instruct:Is the Qwen3-VL Vision Encoder Based on siglip2-so400m-patch16?
new activity
14 days ago
Qwen/Qwen3-Omni-30B-A3B-Instruct:Would you release the pre-trained AuT model?
new activity
18 days ago
XiaomiMiMo/MiMo-Audio-7B-Instruct:Multilingual? Not as good as in the demo video...
Organizations
