AI Paper Atlas

Research map / Benchmarks / HumanEval

HumanEval leaderboard

235 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on HumanEval. Best pass@1: 99.1 (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.

HumanEval · pass@1

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

128 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

HumanEval · accuracy

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

#accuracy ↑MethodPaperTopic
199.4EG-CFG
DeepSeek-V3-0324
Execution Guided Line-by-Line Code Generation
NeurIPS 2025 · Table: Performance on the Huma
Agents, code and math
298.2NAD-kNN
Qwen3-4B-Think
Do LLMs Signal When They’re Right? Evidence from Neuron Agreement
ICML 2026 · Table 1
Reasoning and chain of thought
397MAS2
Qwen3-8B meta-agents
MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems
ICLR 2026 · Table 1
LLM agents
496Terminator cross-domain trainingTERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
NeurIPS 2026 · Table (cross vs single domain)
Reasoning and chain of thought
595.83CARD
deepseek-v3
CARD: Towards Conditional Design of Multi-agent Topological Structures
ICLR 2026 · Table 1
LLM agents
695.1Orthrus-Qwen3-8B
Qwen3-8B
Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
NeurIPS 2026 · Table 2
Language, safety and interpretability
795.01SafeSieve (ours)
deepseek-V3-671B
SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication
AAAI 2026 · Table 1
LLM agents
894.51MESA
Qwen3-30B-A3B
MESA: Improving MoE Safety Alignment via Decentralized Expertise
ICML 2026 · Table 1
Language, safety and interpretability
994.23MAGENavigating the Energy Landscape of Collaboration: Multi-Agent Communication Graph Generation via Score-Based Diffusion
ICML 2026 · Table 1
LLM agents
1094.2HiVA
Qwen2.5-72B-Instruct-Turbo
HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution
AAAI 2026 · Table 1
LLM agents
61 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

HumanEval · score

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

#score ↑MethodPaperTopic
193.74FlowBot
GPT-4.1 mini
FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients
ICML 2026 · Table 3
Agents, code and math
287.8InfiFPO
Phi-4
InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models
NeurIPS 2025 · Table Main Results
Alignment and preferences
386.58Ultra-253B-Base
Llama-3.1-405B-Instruct
FFN Fusion: Rethinking Sequential Computation in Large Language Models
NeurIPS 2025 · Table: Comparison of Ultra-253
Attention and transformers
484.86Avengers
10 open-source ~7B models
The Avengers: A Routing Recipe for Collective Intelligence in Language Models
AAAI 2026 · Table 2
Language, safety and interpretability
584.15CGPO
Qwen2.5-7B-Instruct
Boosting Multi-Domain Reasoning of LLMs via Curvature-Guided Policy Optimization
ICLR 2026 · Table 1
Reasoning and chain of thought
666.5Gemma-2-9b fine-tuned
Gemma-2-9b
StringLLM: Understanding the String Processing Capability of Large Language Models
ICLR 2025 · Table: HumanEval, HumanEval+,
Instruction and fine-tuning
763.4dTRPO
Fast-dLLM-v2-7B
dTRPO : Trajectory Reduction in Policy Optimization of Diffusion Large Language Models
ICML 2026 · Table 2
RL from feedback
862.99Transformer-Squared (Few-shot)
Llama3-8B-Instruct
Transformer-Squared: Self-adaptive LLMs
ICLR 2025 · Table: Self-adaptation on unse
Instruction and fine-tuning
961.8NRT-GM
Llama-3.2-3B
Native Reasoning Models: Training Language Models to Reason on Unverifiable Data
ICLR 2026 · Table 3
Reasoning and chain of thought
1061.6PMA
Seed-MoE-10B/100B
Model Merging in Pre-training of Large Language Models
NeurIPS 2025 · text
Language, safety and interpretability
17 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.