#benchmark Repositories
Discover 193 active open source GitHub repositories tagged with #benchmark, accumulating 392,395 total stars (averaging 2,033 stars per project). Leading this topic is sharkdp/hyperfine with 29,314 stars.
193 repositories total
OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc., across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.
VPS Fusion Monster Server Benchmark Script โ the Go version with no environment dependencies is recommended: https://github.com/oneclickvirt/ecs VPS Fusion Monster Server Benchmark Script โ we now recommend the Go version (zero external dependencies): https://github.com/oneclickvirt/ecs
YABS - a simple bash script to estimate Linux server performance using fio, iperf3, & Geekbench
The fastest and most memory efficient lattice Boltzmann CFD software, running on all GPUs and CPUs via OpenCL. Free for non-commercial use.
Kodezi Chronos is a debugging-first language model that achieves state-of-the-art results on SWE-bench Lite (80.33%) and 67% real-world fix accuracy, over six times better than GPT-4. Built with Adaptive Graph-Guided Retrieval and Persistent Debug Memory. Model available Q1 2026 via Kodezi OS.
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness compatibility checks, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior. Ships reusable CI templates that bring every check to any repository.
Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
A series of large language models developed by Baichuan Intelligent Technology
XcodeBenchmark measures the compilation time of a large codebase on iMac, MacBook, and Mac Pro
MTEB: State-of-the-art evaluation of embeddings across languages and modalities
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
AI API Relay Recommendations and Reviews: Relay Rankings, Relay Testing, Claude / GPT / Gemini Relay Comparison ยท AI API Relay Rankings ยท Folkbench Switch for Claude Code, Codex & Gemini CLI
The Phoronix Test Suite open-source, cross-platform automated testing/benchmarking software.
Prime number projects in 100+ programming languages, to compare their speed - and their programmer's cleverness
CPU-X is a Free software that gathers information on CPU, motherboard and more
Tsung is a high-performance benchmark framework for various protocols including HTTP, XMPP, LDAP, etc.
[NeurIPS 2026] Safety failures in coding agents and frontier LLMs. Reproducible workspaces for studying when AI agents generate unsafe data during task completion.
Java web common vulnerabilities and security code which is based on Spring Boot and Spring Security
ฯ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
VPS Fusion Monster โ Server Benchmark (Go Edition) aims to be the most comprehensive and fastest server benchmarking project. Built in Go, with no external dependencies. VPS Fusion Monster Server Benchmark Project ยท Go Edition. Dedicated to becoming the most comprehensive and fastest server benchmarking project, implemented in Go, with no environmental dependencies and no ads.
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
Cista is a simple, high-performance, zero-copy C++ serialization & reflection library.
๐ฐ Must-read papers and blogs on LLM based Long Context Modeling ๐ฅ
ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.
Frequently Asked Questions
What is the most popular #benchmark repository on GitHub?
The top ranked open source #benchmark project on GitHub is sharkdp/hyperfine with 29,314 stars. A command-line benchmarking tool
Which programming languages are most used in #benchmark repositories?
Among the top ranked #benchmark projects on GitHub, the most common programming languages are Python, C++, C, Rust.
How is the #benchmark repository ranking calculated?
We track 193 active open source repositories tagged with #benchmark (500+ stars), totaling 392,395 stars with an average of 2,033 stars per repository. Rankings update daily from the GitHub API.