List your company

Zero-shot LLM Evaluation Suite (AE, AC, SciQ, MM, MM-P, HS, OBQA, PIQA, RACE, WG, CSQA, AGI)

67.97AE ScoreAMO
65.21465.929566.64567.3605May 18, 2026

Evaluation results

MethodLinks
AMOBackbone=Llama3.1-1.4B, Pre-training token budget=2x Chinchilla optimal ratio2026.0567.9732.1386.424.666.8439.124.670.953453.5921.717.7239.97
Muon-KJBackbone=Llama3.1-1.4B, Pre-training token budget=2x Chinchilla optimal ratio2026.0565.3230.4185.225.476.9437.3224.669.3632.1553.6719.9917.438.99