github.com
Curated list of top Hugging Face models for NLP, vision, and audio tasks with demos and benchmarks.
Directory
Search results
Published directory entries matching your search.
Filters
github.com
Curated list of free and open-source MySQL software, libraries, tools and resources. The README organizes entries into categories such as Analysis, Backup, Benchmarking, Binlog Replication, Connectors, GUI and Replication, and the list accepts and encourages pull requests.
towardsdatascience.com
A Towards Data Science article by Hui Wen Goh evaluating popular hallucination detectors, including G-eval, Ragas and the Trustworthy Language Model, across four public RAG datasets. Using AUROC and precision/recall, it reports how well the methods automatically flag incorrect LLM responses in retrieval-augmented generation systems.
github.com
GPT Migrate team is working on adding for the agent.
browserbench.org
BrowserBench.org hosts browser benchmarks. Speedometer measures the responsiveness of web applications and is maintained by major browser engine developers under an open governance model. JetStream 3.0 is a JavaScript and WebAssembly benchmark suite focused on advanced web applications. MotionMark tests browser graphics systems.
capframex.com
CapFrameX is a benchmarking tool based on Intel's PresentMon that records frames per second, frametimes and sensor measurements while a game runs. It provides overlays via RivaTuner Statistics Server and offers analysis features such as graphs, percentiles and aggregation of runs, plus a cloud service for sharing results.
ccsiobench.com
CCSIO Benchmark is a Windows tool that measures the maximum sequential read/write speed achievable for a volume and the file stack beneath it. It cycles through combinations of IO buffer count, buffer size and caching mode to find the combination delivering the highest throughput. It can assess local drives, remote network shares and virtual devices such as RAM disks and encrypted file containers.
codeflash.ai
Codeflash uses AI to automatically find the most optimized version of your Python code through benchmarking — while verifying it's correct.
github.com
CodeGeeX is an open multilingual code generation model with 13 billion parameters, pre-trained on a code corpus of more than 20 programming languages. It supports multilingual code generation, crosslingual code translation and a VS Code extension, and the repository also releases the HumanEval-X benchmark.
cognition.com
Cognition operates Devin, described as an autonomous software engineer that plans, writes, tests, and ships production code inside existing workflows. The company also publishes FrontierCode, a benchmark intended to measure whether a model writes code a maintainer would merge. Cognition builds tools for software creation.
crystalmark.info
CrystalDiskMark is a disk benchmark tool for Windows. It measures sequential and random read, write, and mixed performance, with several measure modes. It runs on Windows XP through 11 and Windows Server editions on x86, x64, and ARM64 architectures. The documentation notes that benchmarks may shorten SSD or USB memory life and that results are not compatible between major versions.
ego-exo4d-data.org
Ego-Exo4D is a large-scale multi-modal, multi-view video dataset and benchmark of simultaneously captured ego-centric and exo-centric video of skilled human activities such as sports, music, dance, and bike repair. It includes natural language datasets, multi-view capture with Aria glasses and GoPros, and benchmarks including Keystep Recognition and Proficiency Estimation.
github.com
DeepSWE is a GitHub repository that provides a benchmark for measuring the performance of frontier coding AI agents on original, long-horizon engineering tasks. The repository includes documentation on task format, quickstart guides, and details about supported agents and models.
deepswe.datacurve.ai
DeepSWE is a benchmarking platform that evaluates frontier coding agents on original, long-horizon software engineering tasks. It provides a public leaderboard, task examples, and tracks results across 113 tasks, 91 repositories, 5 programming languages, and 28 models.
deploybase.ai
A market intelligence site for AI compute that tracks live GPU cloud and LLM API pricing, performance benchmarks and market data across AI infrastructure providers. It publishes comparisons of GPU cloud pricing by provider and of LLM performance versus cost, including articles on Azure, AWS, Google Cloud, CoreWeave and Lambda GPU offerings.
designarena.ai
Design Arena is a global crowdsourced benchmark for AI-generated design. It allows users to challenge, vote on, and crown winning design outputs, access category-specific leaderboards for assets including websites, slides, images, video, audio, and code, and use top AI models to generate a wide range of design and development assets. Millions of users across over 190 countries use the platform to discover and compare AI model capabilities.
designarena.ai
DesignArena is a crowdsourced benchmark platform for AI-generated design, described as the world's fastest-growing of its kind. It hosts leaderboards for AI design tasks including website, UI component, data visualization, 3D asset, image, logo, slides, video, and audio generation, as well as comparisons of model performance by preference versus speed and preference versus price. It also offers tools to build AI-powered design projects.
github.com
Detectron2 is Facebook AI Research's next generation library providing detection and segmentation algorithms, succeeding Detectron and maskrcnn-benchmark. It supports computer vision research projects and production applications at Facebook and includes capabilities such as panoptic segmentation, Densepose, Cascade R-CNN, rotated bounding boxes, PointRend, DeepLab, ViTDet and MViTv2. Models can be exported to TorchScript or Caffe2 format for deployment.
devcheck.app
DevCheck Hardware Database presents phone and tablet specifications and benchmarks measured on real hardware in real-world use. It lists devices, SoCs, CPUs and GPUs with rankings by median DevCheck Benchmark score, and includes installed-base insights. It also covers DevCheck Device & System Info for Android, a hardware monitoring and benchmarking app.
dnsperf.com
A DNS speed benchmarking tool that performs an A record lookup for the apex domain name from more than 200 locations worldwide. The lookup time serves as a benchmark of DNS provider performance in different regions and allows debugging of self-hosted DNS servers and testing of routing logic. Test result retention is up to 30 days.
dnsspeedtest.online
A free browser-based DNS speed test that benchmarks DNS-over-HTTPS servers from the user's location in real time. It sends live DoH queries locally without server-side code, times full round trips, and marks unresponsive servers as unavailable. Queries time out after five seconds, and results are intended for relative comparison between servers.
nanobench.ankerl.com
ankerl::nanobench is a platform independent microbenchmarking library for C++11/14/17/20. It provides a simple API and prints benchmark results including time per operation, instructions per operation, cycles per operation, IPC and branch misses.
doesitarm.com
Does It Arm? is a compatibility resource for Apple Silicon processors, including the Apple M5 Max and M5 Pro. It lists apps and games reported to support these processors, and provides associated performance reports and benchmark data. Content is organized into categories such as apps, games, devices, benchmarks, and Homebrew packages.
dontkillmyapp.com
Don't kill my app! addresses Android manufacturers that prioritize battery life over app functionality. It lists vendors including Huawei, Xiaomi, OnePlus, Samsung, Meizu, Asus, Oppo and others, and offers ways to fix app-killing behavior. It also references a DontKillMyApp Benchmark app on the Play Store and a Google IssueTracker template for device-specific issues.