Scene Text Recognition on Union14M (test) benchmark leaderboard · SOTA2 Research

Scene Text Recognition on Union14M (test)

97Curve AccuracyCLIP4STR-L

Evaluation Results

Method	Links
CLIP4STR-L2025.03		97	96.6	87.2	91	91.5	89.9	90.3	91.9
CSD-D2025.03		97	97	87.7	91.8	91.7	89.5	91.7	92.3
CSD-D2025.03		96.5	97.2	88.6	92.8	92.8	90.8	90.2	92.7
CLIP4STR-B2025.03		96.4	96.3	88.6	90.1	91.9	92.2	89.1	92.1
CLIP4STR-L2025.03		96.4	97.2	88.6	90.4	92.7	90.7	89.3	92.2
CLIP4STR-B2025.03		96.3	96.1	86.5	92.2	91.2	88.9	89.9	91.6
LER2026.03		83.3	80.2	71.2	76.8	76.6	78.5	81.5	78.3
OTE-AR2026.03		83.1	82.8	73.5	73.7	79.7	70.3	82.2	77.9
BUSNet2026.03		83	82.3	70.8	77.9	78.8	71.2	82.6	78.1
LPV-B2026.03		82.4	64.6	74.1	81	78.8	81.1	82.8	77.8
CDistNet2026.03		81.7	77.1	72.6	78.2	79.9	79.7	81.1	78.6
RobustScanner2026.03		79.4	68.1	70.5	79.6	71.6	82.5	80.8	76.1
OTE PD2026.03		79.2	76	70	74.3	76	64.2	80.1	74.3
ABINet2026.03		75	61.5	65.3	71.1	72.9	59.1	79.4	69.2
DAN2026.03		74.9	63.3	63.4	70.6	70.2	71.1	76.8	70.1
SATRN2026.03		74.8	64.7	67.1	76.1	72.2	74.1	75.8	72.1
SVTR2026.03		72.4	68.2	54.1	68	71.4	67.7	77	68.4
ASTER2026.03		70.9	82.2	56.7	62.9	73.9	58.5	76.3	68.8
VisionLAN2026.03		70.7	57.2	56.7	63.8	67.6	47.3	74.2	62.5
MORAN2026.03		51.2	15.5	51.3	61.2	43.2	64.1	69.3	50.8
SRN2026.03		49.7	20	50.7	61	43.9	51.5	62.7	48.5
CRNN2026.03		19.4	4.5	34.2	44	16.7	35.7	60.4	30.7