Text-to-Motion Generation on HumanML3D Kinematic Representation (test) benchmark leaderboard · SOTA2 Research

Text-to-Motion Generation on HumanML3D Kinematic Representation (test)

0.603R-Precision@1MotionRFT

Evaluation Results

Method	Links
MotionRFT2026.03		0.603	0.786	0.872	0.052	2.528	9.683
MotionRFT2026.03		0.593	0.781	0.863	0.101	2.544	9.613
EasyTune2026.03		0.591	0.777	0.859	0.069	2.592	9.705
EasyTune2026.03		0.581	0.769	0.855	0.132	2.637	9.465
MLD++2026.03		0.548	0.738	0.829	0.073	2.81	9.658
SoPo2026.03		0.528	0.722	0.827	0.174	2.939	9.584
ParCo2026.03		0.515	0.706	0.801	0.109	2.927	9.576
Real2026.03		0.511	0.703	0.797	0.002	2.974	9.503
ReMoDiffuse2026.03		0.51	0.698	0.795	0.103	2.974	9.018
MLD2026.03		0.504	0.698	0.796	0.45	3.052	9.634
MotionLCM2026.03		0.502	0.698	0.798	0.304	3.012	9.607
MotionMamba2026.03		0.502	0.693	0.792	0.281	3.06	9.871
CoMo2026.03		0.502	0.692	0.79	0.262	3.032	9.936
AttT2M2026.03		0.499	0.69	0.786	0.112	3.038	9.7
T2M-GPT2026.03		0.492	0.679	0.775	0.141	3.121	9.722
MotionDiffuse2026.03		0.491	0.681	0.775	0.63	3.113	9.41
T2M2026.03		0.455	0.636	0.736	1.087	3.347	9.175
MDM2026.03		0.455	0.645	0.749	0.489	3.33	9.92
TM2T2026.03		0.424	0.618	0.729	1.501	3.467	8.589