Review Ranking on Amazon Reviews 2023 (test) benchmark leaderboard · SOTA2 Research

Review Ranking on Amazon Reviews 2023 (test)

0.713N@1 (All_Beauty)RLPO

Evaluation Results

Method	Links
RLPO2026.01		0.713	0.815	0.923	0.806	0.894	0.953	0.703	0.803	0.913	0.781	0.849	0.937	0.931
RLPO2026.01		0.702	0.776	0.877	0.709	0.805	0.891	0.645	0.708	0.827	0.633	0.748	0.829	0.856
SFT2026.01		0.672	0.79	0.916	0.778	0.875	0.946	0.7	0.817	0.927	0.748	0.832	0.884	0.918
RLPO2026.01		0.661	0.751	0.852	0.761	0.847	0.919	0.697	0.778	0.881	0.675	0.768	0.859	0.878
LIPO2026.01		0.63	0.743	0.89	0.668	0.77	0.903	0.658	0.778	0.913	0.718	0.786	0.911	0.904
SFT2026.01		0.61	0.708	0.852	0.736	0.813	0.902	0.656	0.761	0.865	0.668	0.801	0.854	0.868
RLPO2026.01		0.573	0.617	0.791	0.644	0.776	0.86	0.615	0.713	0.799	0.736	0.726	0.811	0.809
SFT2026.01		0.572	0.713	0.815	0.64	0.778	0.87	0.633	0.723	0.828	0.629	0.739	0.829	0.845
SFT2026.01		0.526	0.63	0.774	0.581	0.757	0.837	0.619	0.73	0.805	0.677	0.709	0.787	0.801
BM252026.01		0.509	0.649	0.851	0.523	0.67	0.86	0.523	0.67	0.86	0.504	0.63	0.842	0.853
DPO2026.01		0.467	0.611	0.824	0.527	0.647	0.872	0.49	0.623	0.852	0.519	0.654	0.861	0.853
BM252026.01		0.4	0.518	0.69	0.401	0.529	0.721	0.4	0.531	0.72	0.381	0.491	0.68	0.703
DPO2026.01		0.364	0.457	0.638	0.403	0.437	0.643	0.412	0.442	0.508	0.422	0.479	0.638	0.607
BM252026.01		0.362	0.452	0.513	0.345	0.457	0.637	0.345	0.457	0.637	0.306	0.408	0.59	0.594
LIPO2026.01		0.338	0.457	0.646	0.372	0.513	0.716	0.398	0.431	0.51	0.393	0.537	0.72	0.627
DPO2026.01		0.324	0.388	0.576	0.349	0.42	0.597	0.352	0.389	0.572	0.372	0.402	0.606	0.588
LIPO2026.01		0.297	0.393	0.561	0.348	0.42	0.647	0.301	0.393	0.573	0.311	0.403	0.582	0.612
BM252026.01		0.285	0.365	0.51	0.279	0.377	0.536	0.28	0.377	0.535	0.258	0.339	0.49	0.517
DPO2026.01		0.268	0.311	0.476	0.311	0.352	0.508	0.335	0.409	0.559	0.342	0.377	0.529	0.518