AI Paper Atlas

Research map / Benchmarks / Sudoku

Sudoku leaderboard

15 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Sudoku. Best accuracy: 99.9 (SePO-Generalist, NeurIPS 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.

Sudoku · accuracy

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

#accuracy ↑MethodPaperTopic
199.9SePO-Generalist
Task agent DeepSeek-V3.2, prompt agent Gemini 3.1 Pro Previe
SePO: Self-Evolving Prompt Agent for System Prompt Optimization
NeurIPS 2026 · Table 1
LLM agents
296.5MDM (SearchDiff)
MDM 6M
Search-Augmented Masked Diffusion Models for Constrained Generation
NeurIPS 2026 · Table 4
Fast diffusion sampling
391.9d2-StepMerge
LLaDA-8B-Instruct
d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation
ICML 2026 · Table 4
Reasoning and chain of thought
490.2TMLT r=32On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding
ICML 2025 · Table 1
Attention and transformers
590.17ReCOR
GPT-2
Reinforced Context Order Recovery for Adaptive Reasoning and Planning
NeurIPS 2025 · Table 2
Reasoning and chain of thought
689.49MDM (Top prob. margin)
6M MDM
Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
ICML 2025 · Table: Sudoku
Molecules and proteins
789Prophet
Dream-7B-Instruct
Diffusion Language Model Knows the Answer Before It Decodes
ICLR 2026 · Table 1
Fast diffusion sampling
881.7Learned unmasking policy (UPO)
LLaDA-8B-Instruct
Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies
ICLR 2026 · Table 2
Fast diffusion sampling
980.32ISED
pretrained MNIST model
Data-Efficient Learning with Neural Programs
NeurIPS 2024 · Full Performance Summary, leaf
Agents, code and math
1069.5ES fine-tuned
Qwen-2.5-3B
Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
ICML 2026 · Table 3
Instruction and fine-tuning
5 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.