We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.
-
Updated
Jul 6, 2024 - Python
#
humaneval
Here are 38 public repositories matching this topic...
SkyCode是一个多语言开源编程大模型，采用GPT3模型结构，支持Java, JavaScript, C, C++, Python, Go, shell等多种主流编程语言，并能理解中文注释。模型可以对代码进行补全，拥有强大解题能力，使您从编程中解放出来，专心于解决更重要的问题。| SkyCode is an open source programming model, which adopts the GPT3 model structure. It supports Java, JavaScript, C, C++, Python, Go, shell and other languages, and can understand Chinese comments.
javascript python java go shell openai deepmind codex alphacode gpt-3 gpt3 gpt-neo humaneval polycoder codeparrot
-
Updated
Mar 2, 2023
Behavioral Trust Clustering a thermodynamic governance layer that reduces LLM hallucination by 52% on HumanEval. Drop-in wrapper for any decoder. MIT.
abstention openai-api selective-prediction humaneval llm ollama qwen hallucination-mitigation trust-calibration regulated-ai behavioral-clustering
-
Updated
May 4, 2026 - Python
S₀ Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models
lora mamba hybrid-model fine-tuning state-space-model peft humaneval qwen gated-delta-net recurrent-state
-
Updated
Apr 8, 2026 - Python
Benchmark suite for evaluating LLMs and SLMs on coding and SE tasks. Features HumanEval, MBPP, SWE-bench, and BigCodeBench with an interactive Streamlit UI. Supports cloud APIs (OpenAI, Anthropic, Google) and local models via Ollama. Tracks pass rates, latency, token usage, and costs.
python benchmark evaluation gemini openai code-generation claude streamlit humaneval llm ollama swe-bench mbpp bigcodebench
-
Updated
Apr 23, 2026 - Python
LLM Collaboration for Code Generation
code-generation multi-agent-systems multi-agent-reinforcement-learning humaneval large-language-models code-agent mbpp comlrl openmlrl coophumaneval
-
Updated
May 30, 2026 - Python
Fortytwo Network Node Building AI on Monad
machine-learning ai monad rust-lang testnet ai-agents huggingface-models fortytwo humaneval llm-inference testnet-node monad-testnet node-operator noderunning rust-dataset swarm-inference
-
Updated
Dec 8, 2025 - Shell
Run Claude Code with any foundation model on Amazon Bedrock (43 models) or a self-hosted model on EC2. Includes a HumanEval benchmark.
ec2 bedrock claude humaneval ollama amazon-bedrock litellm claude-code ai-coding-assistant coding-agent
-
Updated
Jun 5, 2026 - Shell
大模型评测平台 — 本地/API/HuggingFace/OpenCompass 三路后端，支持数据生产(Self-Instruct/Evol-Instruct)、长尾场景生成、弱项挖掘、回归分析、污染检测、Bad Case归因。可扩展的 Benchmark 系统和 LLM-as-Judge 自动评分。
python flask humaneval ai-evaluation gsm8k mmlu llm-evaluation benchmark-platform rag-evaluation llm-as-judge opencompass llm-benchmark data-contamination-detection
-
Updated
Jun 3, 2026 - Python
A multi-method LLM evaluation harness for text-to-SQL & code generation — bootstrapped CIs, calibrated LLM-as-judge, cost/latency Pareto frontiers, and a CI regression gate.
-
Updated
May 10, 2026 - Python
Co-evolutionary LLM framework where DARWIN (generator) and PHOENIX (adversary) battle to produce antifragile code. Introduces behavioral fingerprinting — drift predicts degradation (ρ=0.720).
python research agents humaneval llm behavioral-fingerprinting openrouter langgraph qwen3 adversarial-testing
-
Updated
May 1, 2026 - Python
Privacy-utility trade-off analysis for AI code completion using AST-based obfuscation techniques on HumanEval dataset. Measures how variable renaming and comment stripping affect CodeGen model output quality via CodeBLEU and Levenshtein distance metrics.
-
Updated
Jan 9, 2026 - Jupyter Notebook
Improve this page
Add a description, image, and links to the humaneval topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the humaneval topic, visit your repo's landing page and select "manage topics."