AI Paper Atlas

Research map / Benchmarks / COPA

COPA leaderboard

21 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on COPA. Best accuracy: 92 (Sparse (DynamicInfer), ICLR 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.

COPA · accuracy

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

#accuracy ↑MethodPaperTopic
192Sparse (DynamicInfer)
ReluLLaMA-70B
DynamicInfer: Runtime-Aware Sparse Offloading for LLMs Inference on a Consumer-Grade GPU
ICLR 2026 · Table 2
Reasoning and chain of thought
291ZO Fine-tuner
LLaMA-3.1-8B
Learning a Zeroth-Order Optimizer for Fine-Tuning LLMs
ICML 2026 · Table 1
Instruction and fine-tuning
390.6RoBERTa-WinoGrande-ft
RoBERTa
WinoGrande: An Adversarial Winograd Schema Challenge at Scale
AAAI 2020 · Table: transfer results
Retrieval and knowledge
490.24GPT-2+Base
RoBERTa-large
Improving Commonsense Causal Reasoning by Adversarial Training and Data Augmentation
AAAI 2021 · Augmented Data table
Language, safety and interpretability
589ZO-AdaMU (2×)
OPT-13B
ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-Order Optimization
AAAI 2024 · Table: Experiments on OPT-13B
Optimizers
688Hybrid-LoRA
Llama-2-7b
New Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework
ICLR 2026 · Table 1
Instruction and fine-tuning
788MeZO
OPT-13B
Fine-Tuning Language Models with Just Forward Passes
NeurIPS 2023 · Table 1
Pruning and efficient tuning
887(IA)^3
T0-3B
Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
NeurIPS 2022 · Appendix PEFT table
Pruning and efficient tuning
986.7S-MeZO
LLaMA-7b
Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
NeurIPS 2025 · Table: Accuracy of Fine-Tuning
Pruning and efficient tuning
1084PolyNorm
OLMoE-1B-7B
Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models
ICLR 2025 · MoE downstream evaluation tabl
Language, safety and interpretability
11 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.