Language Model Personalization on LaMP standard (full-data) benchmark leaderboard · SOTA2 Research

Language Model Personalization on LaMP standard (full-data)

0.735LaMP-1 ScoreOPPU

Evaluation Results

Method	Links
OPPU2026.01		0.735	0.461	0.433	0.15	0.414	0.455	0.464
PriME2026.01		0.727	0.445	0.476	0.143	0.396	0.447	0.447
PRISP2026.01		0.704	0.529	0.424	0.147	0.408	0.47	0.472
PAG2026.01		0.702	0.389	0.482	0.139	0.392	0.433	0.429
Per-Pcs2026.01		0.698	0.454	0.483	0.139	0.397	0.444	0.442
RAG + PAG2026.01		0.695	0.445	0.444	0.147	0.411	0.469	0.454
NP2026.01		0.599	0.238	0.51	0.133	0.384	0.431	0.379
RAG2026.01		0.584	0.39	0.436	0.143	0.409	0.449	0.423