Datasets › NATS-Bench
NATS-Bench
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) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| 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.
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