Our new X account is live! Follow @wizwand_team for updates

Document Visual Question Answering on MMLongbench doc

45.6Accuracy

GPT-4.1

Updated 4d ago

Evaluation Results

Method	Links
GPT-4.1 2025.12		45.6	49.7	-	-	-	-	-
GPT-4o 2025.12		41.6	42.3	-	-	-	-	-
Lang2Act 2026.01		36.55	-	38.59	31.8	31.46	32.23	33.05
Claude-3.7-Sonnet 2025.12		33.9	38.4	-	-	-	-	-
Pixel-Reasoner 2026.01		33.22	-	37.37	27.19	24.72	32.89	27.97
CogDoc 2025.12		33	31.5	-	-	-	-	-
OpenVLThinker 2026.01		32.71	-	35.23	28.57	26.97	30.23	27.97
Vision-R1 2026.01		32.25	-	32.55	27.65	26.4	29.9	30.51
ThinkLite-VL 2026.01		31.66	-	33.22	24.88	26.97	29.9	27.12
VisionMatters 2026.01		31.66	-	35.91	23.96	29.21	27.91	28.81
VRAG-RL 2026.01		31.55	-	31.54	24.88	30.34	30.23	20.34
FRAG 2025.12		31.3	30.7	-	-	-	-	-
EVisRAG 2026.01		30.97	-	32.55	27.19	25.28	27.57	27.12
R1-Onevision 2026.01		30.5	-	30.54	26.73	27.53	27.57	25.42
MM-Search-R1 2026.01		29.92	-	31.54	25.35	27.53	26.91	22.88
InternVL3-8B 2025.12		29.6	28.8	-	-	-	-	-
Docopilot 2025.12		28.8	23	-	-	-	-	-
GPT-4o mini 2025.12		28.6	29.4	-	-	-	-	-
TOT 2026.01		27.82	-	27.18	22.12	21.91	27.57	25.42
Direct 2026.01		27.59	-	31.21	23.5	27.53	23.59	21.19
MiMo-VL-7B-SFT 2025.12		27.5	27.2	-	-	-	-	-
GOT 2026.01		27.12	-	29.19	21.66	22.47	24.25	22.03
VisDom 2026.01		25.96	-	33.89	21.2	21.35	18.94	21.19
Qwen2.5-VL-72B-Instruct 2025.12		24.9	24.6	-	-	-	-	-
SV-RAG 2025.12		23	24.2	-	-	-	-	-
Qwen2.5-VL-7B-Instruct 2025.12		21.2	20.7	-	-	-	-	-
M3DocRAG 2025.12		21	22.6	-	-	-	-	-
VisRAG 2025.12		18.8	18.3	-	-	-	-	-
mPLUG-DocOwl2 2025.12		13.4	8.9	-	-	-	-	-