Reinforcement Learning on IDP v4 benchmark leaderboard · SOTA2 Research

Reinforcement Learning on IDP v4

75,033,713Average ReturnANN

Evaluation Results

Method	Links
ANN2026.02		75,033,713
ANN-SNN2026.02		38,594,440
DSN2026.02		93,541
ILC-SAN2026.02		93,521
pop-SAN2026.02		93,511
MDC-SAN2026.02		93,501
PT-LIF2026.02		93,481
Vanilla LIF2026.02		93,471