Search Results for "benchmark testing"
Sort By:
Showing 105 open source projects for "benchmark testing"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
1
Superposition Benchmark (Unigine)
GPU benchmark testing graphics performance with realistic 3D scenes.
Superposition Benchmark by Unigine is a powerful GPU stress-testing and benchmarking tool designed to evaluate graphics performance using the Unigine 2 Engine. It features advanced visuals, real-time lighting, and physics simulations to test DirectX and OpenGL performance. Superposition provides detailed results, including frame rates, GPU temperatures, and stability data. -
2
go-web-framework-benchmark
Go web framework benchmark
go-web-framework-benchmark is a benchmark suite for comparing the performance of Go web frameworks. It was created to measure full HTTP request processing instead of only route matching speed. The project runs small real HTTP servers for many stable frameworks and tests a simple /hello endpoint. It can add configurable handler delay to simulate business work such as database calls, cache access, disk writes, socket activity, or microservice calls. The benchmark uses wrk and scripts to... -
3
Drill
Drill is an HTTP load testing application written in Rust
Drill is an HTTP load-testing application written in Rust. The main goal for this project is to build a really lightweight tool as an alternative to other that require JVM and other stuff. You can write benchmark files, in YAML format, describing all the stuff you want to test. It was inspired by Ansible syntax because it is really easy to use and extend. As you can see, you can play with interpolations in different ways. -
4
AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
...These environments require agents to interpret instructions, take actions, and adapt their strategies based on feedback from the environment. AgentBench also includes an evaluation framework that measures success rates, rewards, and task completion performance across different agent implementations. By testing models across diverse scenarios, the benchmark highlights strengths and weaknesses in reasoning, long-term planning, and tool usage. -
Save Up to 91% on Cloud Compute With Spot VMsRun batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
-
5
Mitata
benchmark tooling that loves you
A high-performance JavaScript benchmarking tool designed for fast and accurate performance testing. -
6
BenchmarkTools.jl
A benchmarking framework for the Julia language
BenchmarkTools makes performance tracking of Julia code easy by supplying a framework for writing and running groups of benchmarks as well as comparing benchmark results. This package is used to write and run the benchmarks found in BaseBenchmarks.jl. The CI infrastructure for automated performance testing of the Julia language is not in this package but can be found in Nanosoldier.jl. Our story begins with two packages, "Benchmarks" and "BenchmarkTrackers". The Benchmarks package implemented an execution strategy for collecting and summarizing individual benchmark results, while BenchmarkTrackers implemented a framework for organizing, running, and determining regressions of groups of benchmarks. ... -
7
Shannon
Fully autonomous AI hacker to find actual exploits in your web apps
Shannon is an autonomous AI penetration testing system built to find and prove real, exploitable vulnerabilities in web applications rather than stopping at static warnings or best-guess alerts. It focuses on “proof by exploitation,” meaning it actively hunts for attack vectors in your code and then attempts to execute end-to-end exploits to demonstrate impact. The project blends source-aware analysis with automated web interaction so it can validate issues like injection flaws,... -
8
AICGSecEval
A.S.E (AICGSecEval) is a repository-level AI-generated code security
AICGSecEval is an open-source benchmark framework designed to evaluate the security of code generated by artificial intelligence systems. The project was developed to address concerns that AI-assisted programming tools may produce insecure code containing vulnerabilities such as injection flaws or unsafe logic. The framework constructs evaluation tasks based on real-world software repositories and known vulnerability cases derived from CVE records. By simulating realistic development... -
9
JMH Gradle Plugin
Integrates the JMH benchmarking framework with Gradle
The JMH Gradle Plugin provides integration of the Java Microbenchmark Harness (JMH) into Gradle builds, enabling developers to write and run performance benchmarks directly in their projects. JMH is the de facto standard for writing accurate and reliable Java microbenchmarks, and this plugin automates tasks like generating benchmark sources, compiling them with the required JMH support classes, and packaging runnable benchmark jars. It simplifies the workflow by handling classpath setup and wiring Gradle tasks for running benchmarks. Developers can run benchmarks via Gradle commands, produce reports, and compare performance over time. This reduces the manual effort of setting up JMH, making performance testing a natural part of the development cycle. ... -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
10
Hallucination Leaderboard
Leaderboard Comparing LLM Performance at Producing Hallucinations
Hallucination Leaderboard is an open research project that tracks and compares the tendency of large language models to produce hallucinated or inaccurate information when generating summaries. The project provides a standardized benchmark that evaluates different models using a dedicated hallucination detection system known as the Hallucination Evaluation Model. Each model is tested on document summarization tasks to measure how often generated responses introduce information that is not... -
11
T3MP3ST
Autonomous red teaming platform
T3MP3ST is a multi-agent offensive security framework for authorized red-team research, CTFs, and security education. It wraps an existing AI coding agent with orchestration for reconnaissance, exploit exploration, validation, and reporting. The project can work through a browser War Room or CLI while relying on agents such as Claude Code, Codex, Hermes, or locally hosted models. It emphasizes reproducible benchmark claims, keyless operation, and a clear status table that separates stable... -
12
AutoAgent AI
Autonomous harness engineering
...Instead of manually tuning prompts or workflows, developers define high-level goals in a configuration file, and the system continuously modifies its own tools, orchestration, and logic based on benchmark performance. It operates through a loop of testing, analyzing failures, and refining the agent’s configuration to maximize a scoring metric. The framework uses a single-file agent harness combined with structured tasks and evaluation suites to guide optimization. It runs inside Docker for safe execution and reproducibility. This approach shifts agent development from manual design to automated optimization. ... -
13
FurMark
GPU stress test OpenGL and Vulkan graphics benchmark Windows/Linux
FurMark is an intensive benchmarking tool designed to evaluate the performance of graphics cards using fur rendering algorithms. This tool is particularly effective in generating high workloads that can significantly increase the temperature of the GPU, making it a useful utility for testing the stability and stress tolerance of graphics cards. By simulating demanding rendering tasks, FurMark serves as a comprehensive test for assessing the robustness and thermal performance of GPUs under extreme conditions. FurMark from Geeks3D is a free OpenGL benchmark tool for Windows that can also be used to check the stability of a graphics card thanks to a built-in stress test. ... -
14
mistral.rs
Fast, flexible LLM inference
...It provides multiple entry points for developers, including a CLI for running models locally and an HTTP server that exposes an OpenAI-compatible API surface for easy integration with existing clients. The project includes hardware-aware tooling that can benchmark a system and choose sensible quantization and device-mapping strategies, helping users get strong performance without manual tuning. It also supports serving multiple models from the same server process, enabling routing or quick switching between models depending on workload needs. For user-facing testing, mistral.rs can provide a built-in web UI, and it also offers a dedicated lightweight web chat interface that supports richer interaction patterns. -
15
Prime95
Precision CPU stress testing and benchmarking
Prime95 is a popular software tool used primarily for stress testing and benchmarking computer processors by running intense calculations based on the Mersenne prime search algorithm. This rigorous testing helps users gauge system stability and detect potential issues, particularly useful for overclockers, hardware testers, and enthusiasts aiming for optimal CPU performance. -
16
MSI Kombustor
Advanced OpenGL and Vulkan graphics card stress testing utility
MSI Kombustor is a dedicated GPU stress-testing and benchmarking tool built on top of the popular FurMark engine. It is designed to push graphics cards to their thermal and stability limits, helping users verify cooling performance and overclocking reliability. With support for advanced 3D APIs like OpenGL and Vulkan, Kombustor can generate demanding rendering workloads that simulate real-world GPU pressure. The tool provides MSI users with an exclusive, streamlined interface for testing... -
17
ARC-AGI
The Abstraction and Reasoning Corpus
ARC-AGI is a benchmark dataset and experimental framework designed to evaluate and advance artificial general intelligence by testing systems on abstract reasoning tasks that require human-like problem-solving abilities. It consists of a curated set of tasks where models must infer patterns from input-output examples and apply those rules to new unseen cases, without relying on memorization or prior training data. -
18
RecBole
A unified, comprehensive and efficient recommendation library
A unified, comprehensive and efficient recommendation library. We design general and extensible data structures to unify the formatting and usage of various recommendation datasets. We implement more than 100 commonly used recommendation algorithms and provide formatted copies of 28 recommendation datasets. We support a series of widely adopted evaluation protocols or settings for testing and comparing recommendation algorithms. RecBole is developed based on Python and PyTorch for... -
19
Novabench
Benchmark CPU, GPU, memory, and storage
Novabench is a computer benchmarking software that helps users evaluate and compare the performance of their system’s CPU, GPU, memory, and storage. It offers rapid testing, enabling comparisons across millions of devices and providing insights for troubleshooting, upgrades, and performance optimization. -
20
MiniMax-M2.5
State of the art LLM and coding model
MiniMax-M2.5 is a state-of-the-art foundation model extensively trained with reinforcement learning across hundreds of thousands of real-world environments. It delivers leading performance in coding, agentic tool use, search, and complex office workflows, achieving top benchmark scores such as 80.2% on SWE-Bench Verified and 76.3% on BrowseComp. Designed to reason efficiently and decompose tasks like an experienced architect, M2.5 plans features, structure, and system design before generating code. The model supports full-stack development across web, mobile, and desktop platforms, covering the entire lifecycle from system design to testing and code review. ... -
21
powerMAX
powerMAX is a CPU and GPU burn-in test
powerMAX is a CPU and GPU burn-in tool designed to push your hardware to its absolute thermal and power limits. It helps users uncover stability issues, cooling weaknesses, and power delivery problems by applying maximum, sustained stress to both the processor and graphics card. The utility supports dedicated CPU tests—SSE or AVX—and a demanding GPU 3D rendering test, with the option to run both simultaneously for full-system power load evaluation. Because it does not generate scores or... -
22
JDiskMark
Java Disk Benchmark Utility
JDiskMark is a powerful and versatile disk benchmarking tool written in Java, designed to help accurately measure the performance of your storage devices across different operating systems. Whether you're testing HDDs, SSDs, or network drives, JDiskMark provides reliable insights into your disk's read and write... -
23
Safety-Prompts
Chinese safety prompts for evaluating and improving the safety of LLMs
Safety-Prompts is an open-source repository that provides a curated collection of prompts designed to evaluate and improve the safety behavior of large language models. The project focuses primarily on safety testing scenarios relevant to Chinese language models, though the concepts can be applied to other languages and systems. The prompts are structured to test whether models generate outputs that align with human values and safety guidelines when faced with potentially harmful or sensitive requests. Researchers and developers use the dataset to benchmark how well models avoid unsafe responses and follow alignment constraints. ... -
24
Skiplist-CPP
A tiny KV storage based on skiplist written in C++ language
Skiplist-CPP is a lightweight key-value storage engine implemented in C++ using a skip list as its core data structure. It showcases how a log-structured, ordered index can deliver fast inserts, lookups, and deletes while remaining simple to implement and reason about. The project supplies a compact codebase with a clear separation between the skip list implementation and the storage operations that use it. Beyond in-memory operations, it demonstrates persistence through data dump to disk... -
25
ipbench
A benchmark suite for reliable testing of IP networks.
IPbench allows a distributed network of clients to hammer a server, collating performance figures from the clients (and optionally from the server) and then presenting them in an easly-analysable format.
