Zero-shot Image Classification on Cross-dataset Transfer Suite (ImageNet Source + 10 Targets) benchmark leaderboard · SOTA2 Research

Zero-shot Image Classification on Cross-dataset Transfer Suite (ImageNet Source + 10 Targets)

94.5Caltech AccuracyCoPrompt

Evaluation Results

Method	Links
CoPrompt2025.12		94.5	70.8	90.73	65.67	72.3	86.43	24	67.57	47.07	51.9	69.73	67
Co-CoOp2025.12		94.43	71.02	90.14	65.32	71.88	86.06	22.94	67.36	45.73	45.37	68.21	65.74
MMRL2026.03		94.2	—	91.63	65.78	71.74	85.06	24.78	67.26	43.79	51.95	68.54	66.47
FVG-PT2026.03		94.16	—	89.75	65.56	71.66	86.77	24.75	66.54	45.39	43.77	68.89	65.72
FVG-PT2026.03		94.14	—	91.14	66.46	72.15	86.15	25.44	67.42	44.74	53.43	68.81	66.99
RMAdapter2025.12		94.1	71.37	90.85	65.8	72.65	86.33	24.9	68.36	47.33	51.5	69.96	67.56
FVG-PT2026.03		94.04	—	90.27	65.58	71.25	86.55	24.93	66.93	46.63	43.24	68.81	65.82
KgCoOp2026.03		93.96	—	90.49	65.22	71.05	86.37	23.85	66.86	46.39	41.41	68.49	65.41
MMA2025.12		93.8	71	90.3	66.13	72.07	86.12	25.33	68.17	46.57	49.24	68.32	66.61
CoOp2025.12		93.7	71.51	89.14	64.51	68.71	85.3	18.47	64.15	41.92	46.39	66.55	63.88
CoOp2026.03		93.67	—	90.11	64.23	70	86.52	22.11	65.54	43.97	41.49	68.07	64.57
PromptSRC2025.12		93.6	71.27	90.25	65.7	70.25	86.15	23.9	67.1	46.87	45.5	68.75	65.81
MaPLe2025.12		93.53	70.72	90.49	65.57	72.23	86.2	24.74	67.01	46.49	48.06	68.69	66.3
FVG-PT2026.03		92.29	—	90.54	65.73	68.53	86.14	23.55	66.86	44.86	43.1	68.65	65.03
PromptSRC2026.03		92.13	—	90.9	65.34	68.57	86.12	23.46	66.8	45.04	41.25	67.94	64.76