Text-to-Video Generation on EvalCrafter (test) benchmark leaderboard · SOTA2 Research

Text-to-Video Generation on EvalCrafter (test)

0.191CLIPSIMFP

Evaluation Results

Method	Links
FP2025.08		0.191	0.9985	80.66	63.51	1.674
S2Q-VDiT2025.08		0.1902	0.9985	77.8	66.38	1.562
ViDiT-Q2025.08		0.1895	0.9978	66.23	51.35	0.897
Quarot2025.08		0.1873	0.9977	66.49	52.81	0.899
Q-DiT2025.08		0.1871	0.9987	56.45	43.17	1.482
FP2025.08		0.1844	0.9978	76.64	85.02	3.452
S2Q-VDiT2025.08		0.1838	0.9979	70.5	73.31	3.122
Q-DiT2025.08		0.1835	0.9976	47.96	46.72	2.967
S2Q-VDiT2025.08		0.1819	0.9987	73.45	74.41	3.688
FP2025.08		0.1814	0.9982	78.87	73.17	4.536
ViDiT-Q2025.08		0.1812	0.9976	53.09	59.84	3.04
Quarot2025.08		0.1808	0.9975	51.83	56.79	2.867
Quarot2025.08		0.1805	0.9983	33.1	43.67	3.04
ViDiT-Q2025.08		0.1795	0.998	42.01	48.59	1.85
PTQ4DiT2025.08		0.1789	0.9984	22.93	44.07	2.23
Q-DiT2025.08		0.1787	0.9978	63.15	67.37	2.331
PTQ4DiT2025.08		0.1786	0.9973	42.17	33.69	1.089
SmoothQuant2025.08		0.1782	0.9978	7.24	0.42	0.111
PTQ4DiT2025.08		0.1772	0.9985	58.76	52.6	1.837
SmoothQuant2025.08		0.1762	0.9981	55.18	53.87	1.378
SmoothQuant2025.08		0.1742	0.9976	3.05	14.13	1.026