AI Paper Atlas

Research map / Benchmarks / PIQA (zero-shot)

PIQA (zero-shot) leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on PIQA (zero-shot). Best accuracy: 81.8 (Chinchilla, NeurIPS 2022).

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.

PIQA (zero-shot) · accuracy

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

#accuracy ↑MethodPaperTopic
181.8ChinchillaAn empirical analysis of compute-optimal large language model training
NeurIPS 2022 · Table 5
Pruning and efficient tuning
278.67LAS 16 steps
OPT-66B
LAS: Loss-less ANN-SNN Conversion for Fully Spike-Driven Large Language Models
AAAI 2026 · Table 1
Language, safety and interpretability
376.3Pythia-12B-dedupedPythia: A Suite for Analyzing Large Language Models Across Training and Scaling
ICML 2023 · Raw Benchmark Scores - Zero Sh
Language, safety and interpretability
476.11CQ-4c8b
LLaMA-7b
KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization
NeurIPS 2024 · Table: Accuracy on 3 benchmark
Quantization
572.58FiX
760M, 48B tokens FineWeb-Edu
FiX: Introducing Fine-grained Forget Gate into Softmax Attention
ICML 2026 · Table 1
Attention and transformers
671MoSE (TTT)
GPT2-Medium
MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models
ICML 2026 · Table 2
Mixture of experts
769.53MDM (1.1B)Scaling up Masked Diffusion Models on Text
ICLR 2025 · Language understanding results
Fast diffusion sampling
863.5Leviathan
1.2B decoder
Leviathan: Decoupling Input and Output Representations in Language Models
NeurIPS 2026 · Table 2
Attention and transformers
962.7Duo-1.7B
Duo-1.7B
Scaling Beyond Masked Diffusion Language Models
ICML 2026 · Table 1
Fast diffusion sampling
1058.9LocalRegret
OLMoE-1B-7B, 4B tokens from scratch
Regret Pre-training: Bridging Prior and Posterior Views for Enhanced Knowledge Grounding
ICML 2026 · Table 1
Knowledge distillation

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