AI Paper Atlas

Research map / Benchmarks / NAS-Bench-201 CIFAR-10

NAS-Bench-201 CIFAR-10 leaderboard

30 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on NAS-Bench-201 CIFAR-10. Best accuracy: 95.46 (FairNAD (500 archs), NeurIPS 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

NAS-Bench-201 CIFAR-10 · accuracy

30 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
195.46FairNAD (500 archs)Structuring Open-Ended NAS: Semi-Automated Design Knowledge Structuring with LLMs for Efficient Neural Architecture Search
NeurIPS 2026 · Table 1
Neural architecture search
294.83Ours + Drnas
Drnas
Performance-Aware Mutual Knowledge Distillation for Improving Neural Architecture Search
CVPR 2022 · Table 4
Neural architecture search
394.37r-DARTS (λ=0.75, C10, e=5)Understanding and Enhancing Differentiable Architecture Search from Information Bottleneck Perspective
AAAI 2026 · Table 1
Neural architecture search
494.37SAGE-NASSAGE-NAS: Synergizing LLM-Based Semantic Agent with Graph-Based Evaluator for Neural Architecture Search
ICML 2026 · Table 1
Agents, code and math
594.37OursDynamic Ensemble of Low-Fidelity Experts: Mitigating NAS “Cold-Start”
AAAI 2023 · Table: Search results on NAS-B
Neural architecture search
694.37Shapley-NASShapley-NAS: Discovering Operation Contribution for Neural Architecture Search
CVPR 2022 · NAS-Bench-201 comparison table
Neural architecture search
794.36ParZCParZC: Parametric Zero-Cost Proxies for Efficient NAS
AAAI 2025 · Table 3
Neural architecture search
894.36beta-DARTS$\beta $-DARTS++: Bi-Level Regularization for Proxy-Robust Differentiable Architecture Search
TPAMI 2025 · Table (NAS-Bench-201, search o
Neural architecture search
994.36Λ-DARTS
DARTS
$\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells
ICLR 2023 · Table 1
Neural architecture search
1094.36RF-DARTS
DARTS
Differentiable Architecture Search With Random Features
CVPR 2023 · Table: Comparison with BN-NAS
Neural architecture search
20 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.