AI Paper Atlas

Research map / Benchmarks / ARC-E

ARC-E leaderboard

32 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ARC-E. Best accuracy: 92.4 (InfoSteer intervention, NeurIPS 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.

ARC-E · accuracy

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

#accuracy ↑MethodPaperTopic
192.4InfoSteer intervention
LLaMA-3-8B
Steering Information Utility in Key-Value Memory for Language Model Post-Training
NeurIPS 2025 · Table 1
Instruction and fine-tuning
292.11LD-MoLE
Qwen3-1.7B
LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA Experts
ICLR 2026 · Table 1
Mixture of experts
389.6SKE-Learn (M4)
Llama3-8B-Magpie
Empowering Self-Learning of LLMs: Inner Knowledge Explicitation as a Catalyst
AAAI 2025 · Table 2
Retrieval and knowledge
489.2EDFM
LLaMA-2-7B
Ensemble Distribution Distillation via Flow Matching
ICML 2025 · Table 5
Knowledge distillation
587.5FreeCache + Qwen-1.5B-Instruct guided
Dream-7B-Instruct
FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion
ICLR 2026 · Table 2
Fast diffusion sampling
686.9HyPER
DeepSeek-V2-Lite-Chat
HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction
ICML 2026 · Table 1
Reasoning and chain of thought
785.56BLoB (N=10)
Llama2-7B
BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models
NeurIPS 2024 · Table 1
Instruction and fine-tuning
884.38C-LoRA (M=10)
LLaMA2-7B
C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models
NeurIPS 2025 · In-distribution results table
Instruction and fine-tuning
982.42HCInfer
Qwen-30B-A3B (4-bit)
HCInfer: An Efficient Inference System via Heterogeneous Error Compensation for Resource-Constrained Devices
NeurIPS 2026 · Table 1
Quantization
1081.19LLaDA + WINO
LLaDA-8B-Instruct
Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs
ICLR 2026 · Table 1
Language, safety and interpretability
22 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.