List your company

LLM Behavioral Profiling on MTI 4-Axis Battery

56R Scorellama3.1-base
9.221.3533.545.65Apr 2, 2026

Evaluation results

MethodLinks
llama3.1-baseSize=8B2026.045601254——
phi4-miniSize=3.8B2026.044402296——
deepseek-r1Size=8B2026.0441302875——
exaone3.5Size=7.8B2026.043903394——
mistralSize=7B2026.0435701895——
smollm2Size=1.7B2026.0430701393——
gemma2Size=9B2026.04221003397——
qwen3Size=8B2026.042003892——
llama3.1Size=8B2026.0416501495——
gemma3Size=4B2026.0411503497——