Visual Grounding on Chest X-ray Visual Grounding

69.29Aortic Enlargement ScoreOracle

Evaluation results

Method
Oracle2026.02	69.29	63.19	23.92	76.77	63.68	49.34	58.74	49.01	19.06	47.33	32.63	78.34	56.31	56.2
ToolSelect2026.02	67.16	52.06	19.72	72.6	59.56	34.23	41.72	36.61	15.82	34.25	26.81	63.98	48.39	50.08
AG-KD2026.02	66.25	33.41	17.33	70.12	39.45	22.9	31.48	28.71	7.58	12.7	22.55	45.84	32.96	40.66
AutoMix2026.02	65.73	40.25	5.59	69.05	45.8	29.61	39.71	31.54	8.01	19.97	18.57	54.13	35.21	45.94
Causal LLM Router2026.02	65.73	40.25	5.59	69.05	45.8	29.61	39.71	31.54	8.01	19.97	18.57	54.12	35.21	45.94
MF Router2026.02	64.91	40.25	5.59	68.75	45.8	30.22	39.71	32.19	8.01	17.29	17.66	53.79	34.83	45.42
Graph Router2026.02	64.03	40.25	2.76	70.13	45.8	30.14	39.71	31.57	9.08	22.9	19.13	55.17	35.07	45.92
Hybrid LLM2026.02	59.88	39.7	2.78	50.17	33.97	31.79	37.11	28.34	5.27	16.1	14.75	45.49	30.2	38.38
ChEX2026.02	53	49.44	18.86	71.5	54.31	14.21	35.99	32.65	13.71	27.72	20.22	59.69	39.42	40.25
RouterDC2026.02	51.16	39.55	3.11	65.13	30.71	28.69	37.5	21.3	8.05	5.89	15.2	46.25	27.12	38.79
Random2026.02	37.76	30.37	9.21	56.78	34.67	25.5	27.14	22.68	7.77	20.45	13.88	50.9	10.12	32.41
Elo Router2026.02	27.61	5.44	1.61	42.36	6.95	12.32	4.34	2.85	3.06	7.72	4.33	18.44	1.87	20.43
SVM Router2026.02	27.58	5.44	1.61	42.36	6.95	12.32	4.34	2.85	3.06	7.72	4.33	18.44	1.87	20.42
MLP Router2026.02	27.58	5.44	1.61	42.19	6.95	12.32	4.34	2.85	3.06	7.72	4.33	18.44	1.87	20.38
KNN Router2026.02	27.42	5.44	1.61	42.36	6.95	12.32	4.34	2.85	3.06	7.72	4.33	18.37	1.87	20.37
MDETR-AGPT2026.02	25.84	6.8	1.06	40.52	6.19	14.11	5.07	5.18	2.91	6.29	3.1	18.96	1.76	16.52
RadVLM2026.02	18.99	29.9	10.24	52.96	25.02	23.78	19.71	16.92	5.52	11.32	14.29	39.51	18.45	23.14
MAIRA-22026.02	16.34	13.19	6.11	38.32	14	17.18	13.18	11.32	1.81	3.04	5.81	24.18	4.6	16.67
TransVG-AGPT2026.02	14.37	5.98	1.74	41.52	13.12	13.24	11.57	5.92	2.23	4.08	1.73	16.83	3.22	14.06