Datasets › NATS-Bench

NATS-Bench

Introduced by Xuanyi Dong et al. in NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size archive 2025-07-28

A unified benchmark on searching for both topology and size, for (almost) any up-to-date NAS algorithm. NATS-Bench includes the search space of 15,625 neural cell candidates for architecture topology and 32,768 for architecture size on three datasets.

Source: NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size

Benchmarks archive 2025-07-28

All 5 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 1 newer paper was 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): Neural Architecture Search · NATS-Bench Topology, ImageNet16-120 (1 judged, 0 placed), Neural Architecture Search · NATS-Bench Topology, CIFAR-10 (1 judged, 0 placed), Neural Architecture Search · NATS-Bench Topology, CIFAR-100 (1 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
Neural Architecture Search NATS-Bench Topology, ImageNet16-120 LayerNAS Test Accuracy 46.58±0.59 LayerNAS: Neural Architecture Search in Polynomial Complexity — 11 Compare
Neural Architecture Search NATS-Bench Topology, CIFAR-10 LayerNAS Test Accuracy 94.34±0.12 LayerNAS: Neural Architecture Search in Polynomial Complexity — 11 Compare
Neural Architecture Search NATS-Bench Topology, CIFAR-100 LayerNAS Test Accuracy 73.01±0.63 LayerNAS: Neural Architecture Search in Polynomial Complexity — 11 Compare
Neural Architecture Search NATS-Bench Size, CIFAR-100 GreenMachine-2 Kendall's Tau 0.769 GreenMachine: Automatic Design of Zero-Cost Proxies for... RodriguesGabriel/greenmachine 5 Compare
Neural Architecture Search NATS-Bench Size, ImageNet16-120 GreenMachine-2 Kendall's Tau 0.856 GreenMachine: Automatic Design of Zero-Cost Proxies for... RodriguesGabriel/greenmachine 4 Compare

Papers archive 2025-07-28

papers with a benchmark row: 10 · with a code link: 7 · where Syntology ran a sample: 3 (2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (3 of 10 with a benchmark row: 2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 10 of 10 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 43. 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
GreenMachine: Automatic Design of Zero-Cost Proxies for Energy-Efficient NAS 1 15 22 Nov 2024 not harvested
LayerNAS: Neural Architecture Search in Polynomial Complexity 0 5 23 Apr 2023 not harvested
Generalization Properties of NAS under Activation and Skip Connection Search 0 3 15 Sep 2022 not harvested
KNAS: Green Neural Architecture Search 1 3 26 Nov 2021 official (archive's flag): 6 ran · 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 6 samples that ran constructed an object rather than computing a result
NASI: Label- and Data-agnostic Neural Architecture Search at Initialization 0 3 2 Sep 2021 not harvested
BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search 1 1 23 Mar 2021 not harvested
Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective 4 3 23 Feb 2021 official (archive's flag): 1 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) · 2 unverified (2 pointer-only for licence)
FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search 2 3 3 Jul 2019 not harvested
Regularized Evolution for Image Classifier Architecture Search 5 3 5 Feb 2018 not harvested
Proximal Policy Optimization Algorithms 188 3 20 Jul 2017 99 ran (of which 53 constructed an object rather than computing a result; 71 with no instrument failure: 7 honoured, 2 violated, 62 with no contract checked; 28 where Syntology's instrument failed) · 77 unverified (94 pointer-only for licence)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • NATS-Bench Topology, ImageNet16-120
  • NATS-Bench Topology, CIFAR-100
  • NATS-Bench Topology, CIFAR-10
  • NATS-Bench Size, ImageNet16-120
  • NATS-Bench Size
  • NATS-Bench Size, CIFAR-100
  • NATS-Bench Size, CIFAR-10
  • NATS-Bench

8 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