AI Paper Atlas

Research map / Benchmarks / HellaSwag

HellaSwag leaderboard

101 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on HellaSwag. Best accuracy: 96 (DataGen-generated dataset, ICLR 2025).

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.

HellaSwag · accuracy

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

#accuracy ↑MethodPaperTopic
196DataGen-generated dataset
ChatGPT
DataGen: Unified Synthetic Dataset Generation via Large Language Models
ICLR 2025 · Main results on generated and
Agents, code and math
295.7InfoSteer intervention
Gemma-2-9B
Steering Information Utility in Key-Value Memory for Language Model Post-Training
NeurIPS 2025 · Table 1
Instruction and fine-tuning
395.2LoRA-DA
LLaMA 2-7B
LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis
ICML 2026 · Table 1
Optimizers
493.9UNICORN
T5-11B
UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark
AAAI 2021 · Appendix, Leaderboards
Retrieval and knowledge
593.63Benign
LLaMA-2 7B
Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models
ICLR 2025 · Table: Downstream Task Evaluat
Instruction and fine-tuning
691.2LEPA
Llama 3 8B Instruct
Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving
ICLR 2025 · Table 1
Agents, code and math
788.22InfiGFusion
Phi-4
InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion
NeurIPS 2025 · Main results table
Reasoning and chain of thought
887.3DoRA + Ours
Llama-7B
In-Context Compositional Learning vis Sparse Coding Transformer
NeurIPS 2025 · Results on language modeling t
Attention and transformers
985.58Nemotron-51B
Llama-3.1-70B-Instruct
Puzzle: Distillation-Based NAS for Inference-Optimized LLMs
ICML 2025 · Accuracy comparison table
Reasoning and chain of thought
1085.2DRAGON
RoBERTa-Large
Deep Bidirectional Language-Knowledge Graph Pretraining
NeurIPS 2022 · Table 1
Language, safety and interpretability
80 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

HellaSwag · score

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

#score ↑MethodPaperTopic
187.29InfiFPO
Phi-4
InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models
NeurIPS 2025 · Table Main Results
Alignment and preferences
280.88WizardLM-13b
LLaMA 13B
WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions
ICLR 2024 · Table 1
Instruction and fine-tuning
380.8INPO
LLaMA-3-8B SFT
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
ICLR 2025 · Table 2
RL from feedback
478.8YaRN 7B, s=16
Llama 2 7B
YaRN: Efficient Context Window Extension of Large Language Models
ICLR 2024 · Table: Standardized Benchmarks
Instruction and fine-tuning
576.2RNope-SWARope to Nope and Back Again: A New Hybrid Attention Strategy
NeurIPS 2025 · Table: Comparison of models on
Attention and transformers
666.2AOT unpaired
Merlinite-7B
Distributional Preference Alignment of LLMs via Optimal Transport
NeurIPS 2024 · Table 1
Alignment and preferences
765.43TAID
TinyLlama
TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models
ICLR 2025 · Continued pre-training results
Knowledge distillation
860.1UniGist
Llama-3.1-8B-Instruct
UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
NeurIPS 2025 · Short-context table
Attention and transformers
957.13Patched LLaMa-2-7B-HF
LLaMa-2-7B-HF
Interpreting the Repeated Token Phenomenon in Large Language Models
ICML 2025 · Table: The effect of patching
Language, safety and interpretability
1049.4Kosmos-2
Kosmos-1
Grounding Multimodal Large Language Models to the World
ICLR 2024 · Table: Language task results
Multimodal LLMs
1 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.