Papers › IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning

IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning

25 Oct 2021arXiv:2110.13214archive 2025-07-28

Pan Lu, Liang Qiu, Jiaqi Chen, Tony Xia, Yizhou Zhao, Wei zhang, Zhou Yu, Xiaodan Liang, Song-Chun Zhu

Current visual question answering (VQA) tasks mainly consider answering human-annotated questions for natural images. However, aside from natural images, abstract diagrams with semantic richness are still understudied in visual understanding and reasoning research. In this work, we introduce a new challenge of Icon Question Answering (IconQA) with the goal of answering a question in an icon image context. We release IconQA, a large-scale dataset that consists of 107,439 questions and three sub-tasks: multi-image-choice, multi-text-choice, and filling-in-the-blank. The IconQA dataset is inspired by real-world diagram word problems that highlight the importance of abstract diagram understanding and comprehensive cognitive reasoning. Thus, IconQA requires not only perception skills like object recognition and text understanding, but also diverse cognitive reasoning skills, such as geometric reasoning, commonsense reasoning, and arithmetic reasoning. To facilitate potential IconQA models to learn semantic representations for icon images, we further release an icon dataset Icon645 which contains 645,687 colored icons on 377 classes. We conduct extensive user studies and blind experiments and reproduce a wide range of advanced VQA methods to benchmark the IconQA task. Also, we develop a strong IconQA baseline Patch-TRM that applies a pyramid cross-modal Transformer with input diagram embeddings pre-trained on the icon dataset. IconQA and Icon645 are available at https://iconqa.github.io.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2110.13214")

Code

Syntology Ran 8 of 10 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 8 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lupantech/iconqa officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested; 8 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

8ran
2unverified

Licence: 10 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from lupantech/iconqa. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

FeedForward lupantech/iconqa/models/patch_transformer.py official repository ran · metamorphic tier: invariant no licence file found · pointer only · 70a60350f9232fa0 · report
FixedPositionalEncoding lupantech/iconqa/models/patch_transformer.py official repository ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 32a157a43c3680dd · report
LearnedPositionalEncoding lupantech/iconqa/models/patch_transformer.py official repository ran · metamorphic tier: invariant no licence file found · pointer only · 5e976c791ed7236c · report
PreNorm lupantech/iconqa/models/patch_transformer.py official repository ran · metamorphic tier: invariant no licence file found · pointer only · ed1bc00b0c3d787f · report
PreNormDrop lupantech/iconqa/models/patch_transformer.py official repository ran · metamorphic tier: invariant no licence file found · pointer only · 0794d86374d2ab7b · report
SelfAttention lupantech/iconqa/models/patch_transformer.py official repository ran · metamorphic tier: invariant no licence file found · pointer only · b5225e9c0e0545db · report
TransformerModel lupantech/iconqa/models/patch_transformer.py official repository ran · metamorphic tier: invariant no licence file found · pointer only · f02128fda0c13b23 · report
VisionTransformer lupantech/iconqa/models/patch_transformer.py official repository ran fingerprinted no licence file found · pointer only · 81aa9d1ddc833ef9 · report
Patch_Transformer lupantech/iconqa/models/patch_transformer.py official repository unverified no licence file found · pointer only · 0655e3d57f781937 · report
Patch_Transformer lupantech/iconqa/models/patch_transformer.py official repository unverified no licence file found · pointer only · edac4fe5889be9fc · report

Tasks

Arithmetic ReasoningMath Word Problem SolvingMathematical Question AnsweringMathematical ReasoningObject RecognitionQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Datasets

Introduced by this paper, per the archive.

Icon645IconQA

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering (VQA) IconQA Patch-TRM Reasoning (Alg.) 56.73 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Patch-TRM Reasoning (Com.) 87.00 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Patch-TRM Reasoning (Cou.) 77.81 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Patch-TRM Reasoning (Est.) 98.24 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Patch-TRM Reasoning (Fra.) 82.13 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Patch-TRM Reasoning (Geo.) 81.87 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Patch-TRM Reasoning (Mea.) 97.98 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Patch-TRM Reasoning (Pat.) 68.75 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Patch-TRM Reasoning (Pro.) 95.73 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Patch-TRM Reasoning (Sce.) 62.39 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Patch-TRM Reasoning (Sen.) 92.49 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Patch-TRM Reasoning (Spa.) 55.62 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Patch-TRM Reasoning (Tim.) 77.98 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Patch-TRM Sub-tasks (Blank) 83.62 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Patch-TRM Sub-tasks (Img.) 82.66 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Patch-TRM Sub-tasks (Txt.) 75.19 #1 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Reasoning (Alg.) 50.55 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Reasoning (Com.) 84.95 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Reasoning (Cou.) 71.13 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Reasoning (Est.) 99.02 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Reasoning (Fra.) 75.81 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Reasoning (Geo.) 82.61 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Reasoning (Mea.) 98.91 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Reasoning (Pat.) 59.22 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Reasoning (Pro.) 87.65 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Reasoning (Sce.) 66.72 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Reasoning (Sen.) 86.10 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Reasoning (Spa.) 53.38 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Reasoning (Tim.) 69.99 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Sub-tasks (Blank) 79.27 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Sub-tasks (Img.) 79.67 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLT Sub-tasks (Txt.) 72.69 #2 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Reasoning (Alg.) 51.10 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Reasoning (Com.) 82.12 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Reasoning (Cou.) 70.84 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Reasoning (Est.) 98.95 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Reasoning (Fra.) 77.41 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Reasoning (Geo.) 82.60 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Reasoning (Mea.) 98.76 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Reasoning (Pat.) 58.46 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Reasoning (Pro.) 86.07 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Reasoning (Sce.) 68.80 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Reasoning (Sen.) 84.72 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Reasoning (Spa.) 54.64 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Reasoning (Tim.) 68.66 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Sub-tasks (Blank) 78.92 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Sub-tasks (Img.) 79.15 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViT Sub-tasks (Txt.) 72.34 #3 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Reasoning (Alg.) 49.18 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Reasoning (Com.) 83.67 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Reasoning (Cou.) 71.01 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Reasoning (Est.) 99.41 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Reasoning (Fra.) 78.37 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Reasoning (Geo.) 81.31 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Reasoning (Mea.) 99.38 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Reasoning (Pat.) 60.81 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Reasoning (Pro.) 87.84 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Reasoning (Sce.) 61.25 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Reasoning (Sen.) 86.10 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Reasoning (Spa.) 48.34 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Reasoning (Tim.) 69.77 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Sub-tasks (Blank) 78.53 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Sub-tasks (Img.) 78.71 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA UNITER Sub-tasks (Txt.) 72.39 #4 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Reasoning (Alg.) 50.27 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Reasoning (Com.) 81.69 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Reasoning (Cou.) 70.68 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Reasoning (Est.) 99.02 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Reasoning (Fra.) 77.60 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Reasoning (Geo.) 81.80 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Reasoning (Mea.) 98.83 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Reasoning (Pat.) 56.60 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Reasoning (Pro.) 85.70 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Reasoning (Sce.) 67.01 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Reasoning (Sen.) 84.11 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Reasoning (Spa.) 51.42 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Reasoning (Tim.) 67.72 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Sub-tasks (Blank) 78.28 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Sub-tasks (Img.) 77.72 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA DFAF Sub-tasks (Txt.) 72.17 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Reasoning (Alg.) 47.32 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Reasoning (Com.) 82.73 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Reasoning (Cou.) 68.94 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Reasoning (Est.) 99.08 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Reasoning (Fra.) 76.20 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Reasoning (Geo.) 79.86 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Reasoning (Mea.) 98.99 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Reasoning (Pat.) 54.79 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Reasoning (Pro.) 84.87 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Reasoning (Sce.) 62.49 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Reasoning (Sen.) 83.25 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Reasoning (Spa.) 49.70 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Reasoning (Tim.) 68.00 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Sub-tasks (Blank) 74.52 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Sub-tasks (Img.) 77.36 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA MCAN Sub-tasks (Txt.) 71.25 #6 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Reasoning (Alg.) 50.62 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Reasoning (Com.) 75.60 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Reasoning (Cou.) 71.05 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Reasoning (Est.) 99.22 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Reasoning (Fra.) 74.09 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Reasoning (Geo.) 80.05 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Reasoning (Mea.) 99.07 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Reasoning (Pat.) 62.78 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Reasoning (Pro.) 70.94 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Reasoning (Sce.) 58.52 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Reasoning (Sen.) 81.78 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Reasoning (Spa.) 49.46 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Reasoning (Tim.) 66.72 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Sub-tasks (Blank) 77.08 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Sub-tasks (Img.) 76.66 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA ViLBERT Sub-tasks (Txt.) 70.47 #7 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Reasoning (Alg.) 47.46 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Reasoning (Com.) 82.12 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Reasoning (Cou.) 67.56 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Reasoning (Est.) 97.06 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Reasoning (Fra.) 73.77 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Reasoning (Geo.) 79.99 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Reasoning (Mea.) 96.50 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Reasoning (Pat.) 55.67 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Reasoning (Pro.) 82.45 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Reasoning (Sce.) 66.92 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Reasoning (Sen.) 82.12 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Reasoning (Spa.) 53.20 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Reasoning (Tim.) 66.50 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Sub-tasks (Blank) 75.54 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Sub-tasks (Img.) 76.33 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA BAN Sub-tasks (Txt.) 70.82 #8 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Reasoning (Alg.) 50.00 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Reasoning (Com.) 80.65 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Reasoning (Cou.) 65.01 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Reasoning (Est.) 99.54 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Reasoning (Fra.) 72.43 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Reasoning (Geo.) 80.07 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Reasoning (Mea.) 99.46 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Reasoning (Pat.) 55.01 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Reasoning (Pro.) 83.75 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Reasoning (Sce.) 58.22 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Reasoning (Sen.) 84.54 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Reasoning (Spa.) 45.78 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Reasoning (Tim.) 68.28 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Sub-tasks (Blank) 73.03 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Sub-tasks (Img.) 75.92 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Top-Down Sub-tasks (Txt.) 68.51 #9 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Reasoning (Alg.) 11.12 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Reasoning (Com.) 41.20 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Reasoning (Cou.) 18.38 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Reasoning (Est.) 3.62 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Reasoning (Fra.) 34.84 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Reasoning (Geo.) 30.30 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Reasoning (Mea.) 0.36 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Reasoning (Pat.) 34.81 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Reasoning (Pro.) 38.81 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Reasoning (Sce.) 34.25 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Reasoning (Sen.) 45.16 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Reasoning (Spa.) 36.49 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Reasoning (Tim.) 35.82 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Sub-tasks (Blank) 0.29 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Sub-tasks (Img.) 41.70 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Random Sub-tasks (Txt.) 36.87 #10 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Reasoning (Alg.) 28.02 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Reasoning (Com.) 48.19 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Reasoning (Cou.) 33.63 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Reasoning (Est.) 40.46 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Reasoning (Fra.) 33.06 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Reasoning (Geo.) 38.03 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Reasoning (Mea.) 38.07 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Reasoning (Pat.) 33.66 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Reasoning (Pro.) 40.76 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Reasoning (Sce.) 35.37 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Reasoning (Sen.) 45.25 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Reasoning (Spa.) 37.14 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Reasoning (Tim.) 48.09 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Sub-tasks (Blank) 28.45 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Sub-tasks (Img.) 41.64 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA Q-Only Sub-tasks (Txt.) 36.86 #11 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Reasoning (Alg.) 31.73 #12 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Reasoning (Com.) 45.26 #12 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Reasoning (Cou.) 37.64 #12 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Reasoning (Est.) 62.29 #12 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Reasoning (Fra.) 32.48 #12 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Reasoning (Geo.) 38.71 #12 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Reasoning (Mea.) 64.02 #12 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Reasoning (Pat.) 36.29 #12 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Reasoning (Pro.) 37.51 #12 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Reasoning (Sce.) 35.47 #12 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Reasoning (Sen.) 45.25 #12 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Reasoning (Spa.) 37.52 #12 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Reasoning (Tim.) 47.37 #12 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Sub-tasks (Blank) 46.65 #12 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Sub-tasks (Img.) 41.56 #12 of 12 Archive leaderboard report
Visual Question Answering (VQA) IconQA I-Only Sub-tasks (Txt.) 36.02 #12 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections