InfographicVQA

InfographicVQA: Measures visual question answering, OCR, document understanding, chart comprehension, or layout-aware reasoning.

63rows
scoreprimary metric
2026-05-27sampled

Metadata

Metrics

Score, Image span, Question span, Multiple spans, Non span, Table/List, Textual, Visual object, Figure, Map, Comparison, Arithmetic, Counting

Latest Results

Rows are parsed from the official Robust Reading Competition DocVQA Task 3 / InfographicVQA static HTML results table.

Rank Subject Score Model Match Provenance Sampled
1 Human Performance 0.9718 — Imported 2026-05-27
2 Seed-VL-1.5 0.912 — Imported 2026-05-27
3 MiMo-VL-7B-RL 0.8806 — Imported 2026-05-27
4 ORCA 0.8802 — Imported 2026-05-27
5 qwen2.5vl 0.8727 — Imported 2026-05-27
6 qwen2-vl 0.8469 — Imported 2026-05-27
7 InternVL2.5-78B-MPO (generalist) 0.8428 — Imported 2026-05-27
8 Master Thesis 0.8345 — Imported 2026-05-27
9 InternVL2-Pro (generalist) 0.8334 — Imported 2026-05-27
10 Molmo-72B 0.8186 — Imported 2026-05-27
11 MiMo-VL-7B-RL 0.8182 — Imported 2026-05-27
12 test 0.8041 — Imported 2026-05-27
13 InternVL3_5-8B 0.7911 — Imported 2026-05-27
14 1005 0.7893 — Imported 2026-05-27
15 VideoLLaMA3-7B 0.7893 — Imported 2026-05-27
16 LLaVA-One-Vision-1.5-8B-Instruct 0.7842 — Imported 2026-05-27
17 DeepSeek-VL2 0.7814 — Imported 2026-05-27
18 0 0.775 — Imported 2026-05-27
19 LLaVA-One-Vision-1.5-4B-Instruct 0.7612 — Imported 2026-05-27
20 InternVL-1.5-Plus (generalist) 0.7574 — Imported 2026-05-27
21 Ovis2.5-2B 0.7488 — Imported 2026-05-27
22 Zamba2-VL-7B 0.7481 — Imported 2026-05-27
23 ZAYA1-VL-8B 0.7392 — Imported 2026-05-27
24 CATI-VLM 0.7348 — Imported 2026-05-27
25 qwenvl-max (single generalist model) 0.7341 — Imported 2026-05-27
26 GPT-4 Vision Turbo + Amazon Textract OCR 0.7191 — Imported 2026-05-27
27 RALLM 0.7175 — Imported 2026-05-27
28 granite-vision-3.3-2b 0.7024 — Imported 2026-05-27
29 MLCD-Embodied-7B: Multi-label Cluster Discrimination for Visual Representation Learning 0.6998 — Imported 2026-05-27
30 InternLM-XComposer2-4KHD-7B 0.6855 — Imported 2026-05-27
31 llava_onevision_qwen2_7b_si 0.6763 — Imported 2026-05-27
32 Zamba2-VL-2.7B 0.6646 — Imported 2026-05-27
33 SMoLA-PaLI-X Specialist Model 0.6621 — Imported 2026-05-27
34 ScreenAI 5B 0.659 — Imported 2026-05-27
35 SMoLA-PaLI-X Generalist Model 0.6556 — Imported 2026-05-27
36 deepseek_vl2_tiny 0.6396 — Imported 2026-05-27
37 neetolab-sota-v1 0.6195 — Imported 2026-05-27
38 Applica.ai TILT 0.612 — Imported 2026-05-27
39 Zamba2-VL-1.2B 0.607 — Imported 2026-05-27
40 Snowflake Arctic-TILT 0.8B 0.5695 — Imported 2026-05-27
41 PaLI-X (Google Research, Single Generative Model) 0.5477 — Imported 2026-05-27
42 PaliGemma-3B (finetune, 896px) 0.4775 — Imported 2026-05-27
43 loixc-vqa 0.4715 — Imported 2026-05-27
44 llama3-qwenvit 0.4329 — Imported 2026-05-27
45 nnrc_udop_224 0.4299 — Imported 2026-05-27
46 PaliGemma-3B (finetune, 448px) 0.4047 — Imported 2026-05-27
47 pix2struct-large 0.4001 — Imported 2026-05-27
48 tixc-vqa 0.3975 — Imported 2026-05-27
49 IG-BERT (single model) 0.3854 — Imported 2026-05-27
50 pix2struct-base 0.382 — Imported 2026-05-27
51 llama3-internvit 0.3749 — Imported 2026-05-27
52 dolma_multifinetuning 0.3633 — Imported 2026-05-27
53 NAVER CLOVA 0.3219 — Imported 2026-05-27
54 Ensemble LM and VLM 0.2853 — Imported 2026-05-27
55 PaliGemma-3B (finetune, 224px) 0.2846 — Imported 2026-05-27
56 LayoutLMv2 LARGE 0.2829 — Imported 2026-05-27
57 BROS_BASE (WebViCoB 1M) 0.2809 — Imported 2026-05-27
58 InfographicVQA paper model 0.272 — Imported 2026-05-27
59 BERT fuzzy search 0.2078 — Imported 2026-05-27
60 m-rope2 0.1972 — Imported 2026-05-27
61 BERT 0.1678 — Imported 2026-05-27
62 Qwen2.5-VL_InfoVQA 0.1663 — Imported 2026-05-27
63 0710 0.1407 — Imported 2026-05-27