AI Paper Atlas

Research map / Benchmarks / LiveCodeBench

LiveCodeBench leaderboard

35 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on LiveCodeBench. Best pass@1: 76.5 (PGS, ICML 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.

LiveCodeBench · pass@1

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

#pass@1 ↑MethodPaperTopic
176.5PGS
DeepSeek-R1-Distilled-32B
PGS: Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback
ICML 2026 · Table 2 / Table A
Agents, code and math
265.9CRD-30B-A3B
Qwen3-30B-A3B
Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation
NeurIPS 2026 · Table 1
Reasoning and chain of thought
364.2MetaStone-S1-32B-high
QwQ-32B
Test-Time Scaling with Reflective Generative Model
ICLR 2026 · Table 1
Reasoning and chain of thought
462.72Soft (Gumbel)
QwQ-32B
LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinking
ICLR 2026 · Table 2
Reasoning and chain of thought
562.2RPC (P=4096)
QwQ-32B
Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning
NeurIPS 2025 · Accuracy table
Reasoning and chain of thought
658.4E1-code-14B
DeepCoder-14B-Preview
Scalable Chain of Thoughts via Elastic Reasoning
ICLR 2026 · Table 1
Reasoning and chain of thought
757DyCon (Ours)
DeepSeek-R1-Distill-Qwen-7B
DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling
ICML 2026 · Table 2
Reasoning and chain of thought
854.6SxS Interleaved (RL Final)
Qwen3-30B-A3B
When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning
ICML 2026 · Table 2
Reasoning and chain of thought
945.5Difficulty-Flipped
Qwen2.5-Instruct-14B
Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions
NeurIPS 2025 · Table 1
Reasoning and chain of thought
1045.1ICoT
DeepSeek-V3-671B
Intention Chain-of-Thought Prompting with Dynamic Routing for Code Generation
AAAI 2026 · Appendix table
Reasoning and chain of thought
8 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

LiveCodeBench · accuracy

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

#accuracy ↑MethodPaperTopic
196.8Dual verificationrStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset
NeurIPS 2025 · Ablation table: test cases
Agents, code and math
276GSPO + IBPO(mask)
Qwen3-32B
Reducing Credit Assignment Variance via Counterfactual Reasoning Paths
NeurIPS 2026 · Table 1
Reasoning and chain of thought
362.72Soft Thinking w/ Cold Stop
QwQ-32B
Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
NeurIPS 2025 · Ablation table
Reasoning and chain of thought
462OEA k0=5
Qwen3-30B-A3B
Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining
ICML 2026 · Table 1
Mixture of experts
558.68TableLong RL
DS-R1-Distill-32B
Probing How Scalable Table Data Enhances General Long-Context Reasoning
ICML 2026 · Table 4
Language, safety and interpretability
658.2Sonata
Qwen3-8B
Adaptive Thinking: Large Language Models Know When to Think in Latent Space
ICLR 2026 · Table 1
Reasoning and chain of thought
754.4D-ARL
Qwen3-1.7B
D-ARL: A Distribution-Matched Asynchronous Reinforcement Learning Framework for Language Reasoning
ICML 2026 · Table 1
RL from feedback
849.5ShorterBetter-7B (α=2)
DeepSeek-R1-Distill-Qwen-7B
ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning
NeurIPS 2025 · 7B results table
Reasoning and chain of thought
939R2R
R1-1.5B + R1-32B
R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
NeurIPS 2025 · Performance and efficiency com
Reasoning and chain of thought
1037.6RAST + ΔR7B
Qwen-2.5-14B-1M
RAST: Reasoning Activation in LLMs via Small-model Transfer
NeurIPS 2025 · Table 3
Reasoning and chain of thought
7 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.