AI Paper Atlas

Research map / Benchmarks / WinoGrande

WinoGrande leaderboard

68 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on WinoGrande. Best accuracy: 90.29 (GateRA, 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.

WinoGrande · accuracy

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

#accuracy ↑MethodPaperTopic
190.29GateRA
LLaMA-3-8B
GateRA: Token-aware Modulation for Parameter-Efficient Fine-tuning
AAAI 2026 · Table 1
Pruning and efficient tuning
289.6Topology-aligned contrastive loss
Llama-3.1-8B
Syntax vs. Semantics: How Transformers Learn Deep Dependencies
ICML 2026 · Table 2
Reasoning and chain of thought
387.2InfoSteer intervention
Qwen-2.5-7B
Steering Information Utility in Key-Value Memory for Language Model Post-Training
NeurIPS 2025 · Table 1
Instruction and fine-tuning
487.1LoRA-DA
LLaMA 2-7B
LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis
ICML 2026 · Table 1
Optimizers
585.01PortLLM
Mistral-7B
PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches
ICLR 2025 · Table: Zero-shot performance c
Instruction and fine-tuning
684.53Nemotron-51B
Llama-3.1-70B-Instruct
Puzzle: Distillation-Based NAS for Inference-Optimized LLMs
ICML 2025 · Accuracy comparison table
Reasoning and chain of thought
781.2DoRA + Ours
Llama-7B
In-Context Compositional Learning vis Sparse Coding Transformer
NeurIPS 2025 · Results on language modeling t
Attention and transformers
880.6Ours
Qwen 3 4B
Weight Updates as Activation Shifts: A Principled Framework for Steering
ICML 2026 · Table 1
Pruning and efficient tuning
979.98OSV + PSV (AutoPSV)
Mistral-Instruct
AutoPSV: Automated Process-Supervised Verifier
NeurIPS 2024 · Table 5 (commonsense results)
Reasoning and chain of thought
1079.63TBPO-A
Llama 3 8B
TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
ICML 2026 · Table 1
Alignment and preferences
58 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.