Share your thoughts, 1 month free Claude Pro on usSee more

Agricultural Reasoning on AgroMind 1.0 (test)

51.23SL

AgroNVILA-Baseline

Updated 1mo ago

Evaluation Results

Method
AgroNVILA-Baseline 2026.03	51.23	30.64	56.76	84.79	90.09	83.33	38.81	47.01	69.4	52.45	78.3	68.97	44.9	61.61
AgroNVILA-Baseline + VCMN + ARPO 2026.03	50.79	30.95	59.73	84.96	90.48	84.42	44.06	47.22	70.12	55.37	78.11	70.36	43.57	62.47
AgroNVILA-Baseline + VCMN 2026.03	50.74	30.64	57.03	85.02	90.3	84.25	42.31	46.92	69.87	53.05	76.46	70.18	42.67	61.73
NVILA-Lite-8B 2026.03	41.85	25.89	37.47	63.96	49.43	35.75	36.51	21.13	28.62	19.33	24.26	53.49	29.82	35.68
GPT-4o 2026.03	41.38	35.16	33.52	78.55	66.09	55.83	43.9	23.75	46.2	16.1	27.15	69.81	30.9	43.14
Claude-3-Opus 2026.03	40.37	19.91	43.13	74.2	61.48	37.08	45.14	26.87	51.07	20.69	32.61	65.14	34	43.15
GPT-4V 2026.03	39.19	29.94	42.09	74.14	65.61	60.5	41.22	36.85	53.27	28.09	38.33	57.41	38.83	47.29
LLaVA-NeXT-8B 2026.03	35.47	16.41	41.76	57.68	28.7	30	19.51	26.84	34.81	10.59	17.22	37.74	33.48	31.53
LLaVA-NeXT-7B-Mistral 2026.03	33.5	22.66	40.11	44.64	40	36.67	21.95	24.7	36.71	8.05	15.23	39.62	11.59	29.17
TinyLLaVA 2026.03	29.56	17.97	24.73	68.41	23.48	30	24.39	23.99	31.65	3.39	13.91	45.28	9.44	28.01
InternVL-2-4B 2026.03	29.06	23.44	25.27	48.7	44.78	19.17	30.49	19	46.84	19.49	30.46	50.94	12.88	31.15
XComposer2-4K-HD 2026.03	29.06	27.34	32.97	51.88	40	44.17	34.15	22.33	27.53	11.86	37.75	43.4	38.63	33.02
Gemini-1.5-Pro 2026.03	27.59	23.44	24.73	77.39	52.61	45.83	39.02	32.3	47.78	19.92	34.44	66.04	30.04	41.06
Claude-3.5-Sonnet 2026.03	24.14	17.19	40.11	57.97	50	57.5	44.51	24.47	35.44	20.34	33.11	50.94	36.05	37.11
Human 2026.03	19.15	15	40.83	57.6	46.17	47.22	35.49	28.88	39.46	12.33	25.62	34.07	13.5	33.15
Random 2026.03	18.03	17.97	16.48	35.65	25.65	10	24.39	4.99	21.2	9.19	19.87	21.7	26.96	19.24
Mantis-Idefics2 2026.03	16.75	20.31	31.32	63.77	44.35	37.5	22.56	24.23	20.89	8.47	13.91	56.6	30.9	30.41
DeepSeek-VL2-small 2026.03	16.26	20.31	24.18	61.45	28.7	65.83	31.71	19.71	20.57	19.07	19.87	38.68	8.58	28.08
GeoChat 2026.03	14.78	19.53	23.63	48.7	34.78	30.83	16.46	19.48	20.57	8.47	29.8	51.89	24.89	25.93
InstructBLIP-Vicuna-7B 2026.03	9.85	16.41	20.88	33.33	21.74	10.83	19.51	10.93	21.52	4.66	20.53	20.75	11.16	17.39
GeoLLaVA-8K 2026.03	9.85	25.78	17.58	34.78	15.22	7.5	17.68	4.75	16.14	7.63	14.57	34.91	8.58	15.73