AI Paper Atlas

Research map / Benchmarks / MBPP

MBPP leaderboard

149 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MBPP. Best pass@1: 97.66 (Soft (Gumbel), 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.

MBPP · pass@1

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

#pass@1 ↑MethodPaperTopic
197.66Soft (Gumbel)
QwQ-32B
LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinking
ICLR 2026 · Table 2
Reasoning and chain of thought
296.5PGS
Claude-Sonnet-4
PGS: Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback
ICML 2026 · Table 2 / Table A
Agents, code and math
395.1AgentConductor (3B)AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation
ICML 2026 · Table 1
LLM agents
493.7RaLU
DeepSeek V3
Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment
ICML 2025 · Table 1
Reasoning and chain of thought
593.2PADA
Qwen3-4B
PADA-Coder: Improving Plan-Following Code Generation via Perturbation-Verified Attention Distillation and Dynamic Alignment
ICML 2026 · Table 1
Reasoning and chain of thought
691.4rStar-Coder-14B
Qwen2.5-Coder-Instruct-14B
rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset
NeurIPS 2025 · Table 1
Agents, code and math
791.1LCP (Ours)
GPT-3.5-turbo
AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent Framework
ICLR 2026 · Table 3
LLM agents
889.9LessonL
Deepseek7B, Qwen7B, Qwen14B
Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve
NeurIPS 2025 · Table: code generation results
LLM agents
988.1CE-Graph
gpt-4o-mini
Failure-Driven Workflow Refinement
ICML 2026 · Table 1
Graph algorithms and clustering
1087.7MetaGPT (GPT-4)
GPT-4
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
ICLR 2024 · text
LLM agents
74 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

MBPP · accuracy

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

#accuracy ↑MethodPaperTopic
196.6EG-CFG
DeepSeek-V3-0324
Execution Guided Line-by-Line Code Generation
NeurIPS 2025 · Table: Performance on the MBPP
Agents, code and math
296.2SePO-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
393.4Orthrus-Qwen3-8B
Qwen3-8B
Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
NeurIPS 2026 · Table 2
Language, safety and interpretability
492.1HiVA
Qwen2.5-72B-Instruct-Turbo
HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution
AAAI 2026 · Table 1
LLM agents
591.05FLARE-9B (AR-Trust)
Qwen3.5-9B
FLARE: Diffusion for Hybrid Language Model
NeurIPS 2026 · Table 1
Language, safety and interpretability
686.21EvoMAS
GPT-4o-mini
EvoMAS: Heuristics in the Loop—Evolving Smarter Agentic Workflows
ICML 2026 · Table 2
LLM agents
786NAD-kNN
Qwen3-4B-Think
Do LLMs Signal When They’re Right? Evidence from Neuron Agreement
ICML 2026 · Table 1
Reasoning and chain of thought
885.2InfiGFusion
Phi-4
InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion
NeurIPS 2025 · Main results table
Reasoning and chain of thought
985.1MAS2
Qwen3-8B meta-agents
MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems
ICLR 2026 · Table 1
LLM agents
1084.57MAGENavigating the Energy Landscape of Collaboration: Multi-Agent Communication Graph Generation via Score-Based Diffusion
ICML 2026 · Table 1
LLM agents
40 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

MBPP · score

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

#score ↑MethodPaperTopic
182.5InfiFPO
Phi-4
InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models
NeurIPS 2025 · Table Main Results
Alignment and preferences
279.6AoT
DeepSeek-V3
Atom of Thoughts for Markov LLM Test-Time Scaling
NeurIPS 2025 · Performance Comparison table
Reasoning and chain of thought
376.08Avengers
10 open-source ~7B models
The Avengers: A Routing Recipe for Collective Intelligence in Language Models
AAAI 2026 · Table 2
Language, safety and interpretability
473.84FlowBot
GPT-4.1 mini
FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients
ICML 2026 · Table 3
Agents, code and math
566.17PiSSA
Gemma-7B
PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models
NeurIPS 2024 · Table: Comparison of PiSSA and
Pruning and efficient tuning
659.4Dream-Instruct + G-Star
Dream-Instruct 7B
Guided Star-Shaped Masked Diffusion
ICML 2026 · Table 1
Fast diffusion sampling
758+CCD
Dream-7B-Instruct
Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models
ICML 2026 · Table 1
Fast diffusion sampling
855Webscale-RL
Qwen2.5-3B
Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels
ICLR 2026 · Table 1
Reasoning and chain of thought
951.3PaTH
SmolLM2-1.7B
PaTH Attention: Position Encoding via Accumulating Householder Transformations
NeurIPS 2025 · conversion results table
Attention and transformers
1040.6RPT k=1, w=2
8B autoregressive model
Corrector Sampling in Language Models
NeurIPS 2025 · Results table
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.