AI Paper Atlas

Research map / Benchmarks / CIFAR-100 (T=4)

CIFAR-100 (T=4) leaderboard

14 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CIFAR-100 (T=4). Best accuracy: 84.88 (CKDSNN, AAAI 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.

CIFAR-100 (T=4) · accuracy

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

#accuracy ↑MethodPaperTopic
184.88CKDSNN
Spikformer-4-384
A Closer Look at Knowledge Distillation in Spiking Neural Network Training
AAAI 2026 · Table 1
Knowledge distillation
282.85MEOM
ResNet-19
Many Eyes, One Mind: Temporal Multi-Perspective and Progressive Distillation for Spiking Neural Networks
ICLR 2026 · Table 1
Knowledge distillation
382.47Our
ResNet-19
Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment
ICML 2025 · Table 1
Spiking networks
482.29Stable Spike
ResNet-19
Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networks
CVPR 2026 · Appendix table (CIFAR10/100)
Spiking networks
581.27TRE
ResNet-19
Temporal Representation Enhancement (TRE): Learning to Forget Dominant Patterns for Enhanced Temporal Spiking Features
CVPR 2026 · Table 1
Spiking networks
681.03SMixer + DSTSPSMixer: Rethinking Efficient-Training and Event-Driven SNNs
ICLR 2026 · Table 3
Spiking networks
780.26Spike-Driven Transformer + SEMM
Spike-Driven Transformer
Spiking Transformer with Experts Mixture
NeurIPS 2024 · Table 4
Mixture of experts
879.45SSA
SpikingResformer
Efficient Transformer Attention for SNNs via Hadamard Simplification
ICML 2026 · Table 5
Spiking networks
978.42InfLoR-SNN
ResNet19
Reducing Information Loss for Spiking Neural Networks
ECCV 2022 · Table 4
Spiking networks
1077.76KvLIF
ResNet-18
Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks
NeurIPS 2026 · Table 1
Spiking networks
4 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.