Menu
evals.blah.dev
Ctrl+K
Sign In
Compare Models
Compare eval results across models side by side.
Eval Results
Live Chat
Select Models (0/3)
CHUNGUS
LLM1 FineWeb-Edu 124M — 5 min
GPT-2 124M (reference)
alpha-er
alpha-yi-qwen35-9b-chat-v67-20260817
ANDREA-145M-ANNEALED
Spherical KAN Maxine
Steve Agent
alpha-yi
SpectralKAN Lohe SFT
spherical-spectral-kan
spherical-benchmax
ANDREA-145M-BENCHMAX
Steve
ANDREA-145M
Alpha 60M Chat
Compare Evals