Scene Text Recognition on Union14M (CUR MLO ART CTL SAL MLW GEN Metrics) benchmark leaderboard · SOTA2 Research

Scene Text Recognition on Union14M (CUR MLO ART CTL SAL MLW GEN Metrics)

91.71CUR (Curve Accuracy)SVTRv2-AR

Evaluation Results

Method	Links
SVTRv2-AR2026.02		91.71	94.74	79.44	86.01	86.86	86.29	85.47	87.22
SVTRv22026.02		90.6	89	79.3	86.1	86.2	86.7	85.1	86.14
MAERec2026.02		89.1	87.1	79	84.2	86.3	85.9	84.6	85.17
SMTR2026.02		89.1	87.7	76.8	83.9	84.6	89.3	83.7	85
SVTRv2-AR2026.02		88.99	94.45	73.11	80.62	81.68	87.26	74.87	83
PARSeq2026.02		87.6	88.8	76.5	83.4	84.4	84.3	84.9	84.26
LPV2026.02		86.2	78.7	75.8	80.2	82.9	81.6	82.9	81.2
CPPD2026.02		86.2	78.7	76.5	82.9	83.5	81.9	83.5	81.91
OTE2026.02		86	75.8	74.6	74.7	81	65.3	82.3	77.09
CPPD2026.02		83.8	90.8	67.11	75.74	70.06	82.04	69.82	77.05
SVTRv22026.02		83.39	91.31	67.11	77.41	70.31	83.25	71.1	77.7
BUSNet2026.02		83	82.3	70.8	77.9	78.8	71.2	82.6	78.1
SMTR2026.02		80.87	88.31	65.33	76.89	69.24	84.59	71.6	76.69
ABINet2026.02		80.4	69	71.7	74.7	77.6	76.8	79.8	75.72
MAERec2026.02		78.94	90.8	68.44	77.02	71.45	83.01	73.29	77.56
LPV2026.02		78.44	89.85	65	71.63	66.65	81.31	69.25	74.59
SVTR2026.02		76.2	44.5	67.8	78.7	75.2	77.9	77.8	71.17
SVTR2026.02		74.73	86.56	62.44	74.45	62.67	81.8	68.67	73.05
BUSNet2026.02		73.62	87.66	63.44	69.58	62.22	79.61	68.7	72.12
PARSeq2026.02		73.54	88.31	64.89	72.66	68.48	79.85	70.24	74
OTE2026.02		73.54	88.31	64.89	72.66	68.48	79.85	70.24	74
ABINet2026.02		73.04	85.1	58.44	64.31	59.25	77.31	63.98	68.78
ViT-CTC2026.02		70.03	80.5	58	72.53	68.04	73.06	77.56	71.39
ViT-CTC2026.02		68.47	84.59	58	71.12	52.24	79.61	65.71	68.53
CRNN2026.02		48.1	13	51.2	62.3	41.4	60.4	68.2	49.24
CRNN2026.02		33.59	64.21	36.33	49.29	16.49	65.78	48.98	44.95