Datasets › CLEVR

CLEVR (Compositional Language and Elementary Visual Reasoning)

Introduced by Justin Johnson et al. in CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning20 Dec 2016 archive 2025-07-28

CLEVR (Compositional Language and Elementary Visual Reasoning) is a synthetic Visual Question Answering dataset. It contains images of 3D-rendered objects; each image comes with a number of highly compositional questions that fall into different categories. Those categories fall into 5 classes of tasks: Exist, Count, Compare Integer, Query Attribute and Compare Attribute. The CLEVR dataset consists of: a training set of 70k images and 700k questions, a validation set of 15k images and 150k questions, a test set of 15k images and 150k questions about objects, answers, scene graphs and functional programs for all train and validation images and questions. Each object present in the scene, aside of position, is characterized by a set of four attributes: 2 sizes: large, small, 3 shapes: square, cylinder, sphere, 2 material types: rubber, metal, 8 color types: gray, blue, brown, yellow, red, green, purple, cyan, resulting in 96 unique combinations.

Source: On transfer learning using a MAC model variant Image Source: Johnson et al

Benchmarks archive 2025-07-28

All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Syntology 3 newer papers were judged to report on this dataset's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Visual Question Answering (VQA) · CLEVR (3 judged, 0 placed), Visual Question Answering · CLEVR (3 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

First row (archive order)PaperCode
Visual Question Answering (VQA) CLEVR NS-VQA (1K programs) Accuracy 99.8 Neural-Symbolic VQA: Disentangling Reasoning from Vision... kexinyi/ns-vqa +1 15 Compare
Image Generation CLEVR Projected GAN FID-5k-training-steps 0.89 Projected GANs Converge Faster autonomousvision/projected_gan +2 6 Compare
Visual Question Answering CLEVR NeSyCoCo Neuro-Symbolic Accuracy 99.7 NeSyCoCo: A Neuro-Symbolic Concept Composer for... hlr/nesycoco 1 Compare

Papers archive 2025-07-28

papers with a benchmark row: 17 · with a code link: 15 · where Syntology ran a sample: 12 (10 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (12 of 17 with a benchmark row: 10 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 17 of 17 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 657. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional Generalization 1 2 20 Dec 2024 not harvested
Projected GANs Converge Faster 3 1 1 Nov 2021 official (archive's flag): 12 ran · 38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified (6 pointer-only for licence)
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding 5 1 26 Apr 2021 community repositories only · 7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified
Generative Adversarial Transformers 2 5 1 Mar 2021 community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified
Interpretable Visual Reasoning via Induced Symbolic Space 1 1 23 Nov 2020 not harvested
Language-Conditioned Graph Networks for Relational Reasoning 1 1 10 May 2019 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision 2 1 26 Apr 2019 official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified
Explainable and Explicit Visual Reasoning over Scene Graphs 2 1 5 Dec 2018 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding 2 1 4 Oct 2018 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (2 pointer-only for licence)
Question-Guided Hybrid Convolution for Visual Question Answering 0 1 8 Aug 2018 not harvested
Learning Visual Question Answering by Bootstrapping Hard Attention 1 1 1 Aug 2018 not harvested
DDRprog: A CLEVR Differentiable Dynamic Reasoning Programmer 0 1 30 Mar 2018 not harvested
Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning 1 1 14 Mar 2018 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified
Compositional Attention Networks for Machine Reasoning 10 1 8 Mar 2018 community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified
FiLM: Visual Reasoning with a General Conditioning Layer 7 1 22 Sep 2017 official (archive's flag): 1 ran · 9 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (7 pointer-only for licence)
A simple neural network module for relational reasoning 20 1 5 Jun 2017 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (1 pointer-only for licence)
Inferring and Executing Programs for Visual Reasoning 5 1 10 May 2017 official (archive's flag): 2 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (6 pointer-only for licence)

Dataset loaders archive 2025-07-28

3 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

CC BY 4.0

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • CLEVR
  • CLEVR-CoGenT

2 variant names, as the archive lists them.

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