gym-electric-motor (GEM) — Peer-reviewed • Rank 14.2 • Science 98%

gym-electric-motor (GEM): A Python toolbox for the simulation of electric drive systems - Published in JOSS (2021)

DeepBench — Peer-reviewed • Rank 8.6 • Science 95%

DeepBench: A simulation package for physical benchmarking data - Published in JOSS (2025)

ctbench - compile-time benchmarking and analysis — Peer-reviewed • Rank 4.9 • Science 95%

ctbench - compile-time benchmarking and analysis - Published in JOSS (2023)

fastcrypto • Rank 22.3 • Science 67%

Common cryptographic library used in software at Mysten Labs.

yaib • Rank 10.1 • Science 77%

🧪Yet Another ICU Benchmark: a holistic framework for the standardization of clinical prediction model experiments. Provide custom datasets, cohorts, prediction tasks, endpoints, preprocessing, and models. Paper: https://arxiv.org/abs/2306.05109

mmaction2 • Rank 21.3 • Science 64%

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

bigcodebench • Rank 15.3 • Science 64%

[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI

asreview-insights • Rank 12.3 • Science 67%

Tools such as plots and metrics to analyze (simulated) reviews for ASReview LAB

tiny_qa_benchmark_pp • Rank 2.1 • Science 77%

Tiny QA Benchmark++ a micro-benchmark suite (52-item gold + on-demand multilingual synthetic packs), generator CLI, and CI-ready eval harness for ultra-fast LLM smoke-testing & regression-catching.

proteinworkshop • Rank 11.6 • Science 67%

Benchmarking framework for protein representation learning. Includes a large number of pre-training and downstream task datasets, models and training/task utilities. (ICLR 2024)

SciMLBenchmarks • Rank 11.5 • Science 67%

Scientific machine learning (SciML) benchmarks, AI for science, and (differential) equation solvers. Covers Julia, Python (PyTorch, Jax), MATLAB, R

mmpose • Rank 24.4 • Science 54%

OpenMMLab Pose Estimation Toolbox and Benchmark.

seb • Rank 11.3 • Science 67%

A Scandinavian Benchmark for sentence embeddings

trajectopy • Rank 11.1 • Science 67%

Trajectopy - Trajectory Evaluation in Python

babelstream • Rank 10.7 • Science 67%

STREAM, for lots of devices written in many programming models

benchexec • Rank 18.5 • Science 59%

BenchExec: A Framework for Reliable Benchmarking and Resource Measurement

amlb • Rank 13.2 • Science 64%

OpenML AutoML Benchmarking Framework

tasksource • Rank 11.4 • Science 64%

Datasets collection and preprocessings framework for NLP extreme multitask learning

fluidx3d • Rank 8.4 • Science 67%

The fastest and most memory efficient lattice Boltzmann CFD software, running on all GPUs and CPUs via OpenCL. Free for non-commercial use.

BenchmarkPlots • Rank 20.1 • Science 54%

A benchmarking framework for the Julia language

compression_benchmark • Rank 4.8 • Science 67%

Benchmarking FASTQ compression with 'mature' compression algorithms

https://github.com/cheind/py-motmetrics • Rank 22.6 • Science 49%

:bar_chart: Benchmark multiple object trackers (MOT) in Python

lrebench • Rank 4.2 • Science 67%

[EMNLP 2022 Findings] Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study

rl4co • Rank 16.6 • Science 54%

A PyTorch library for all things Reinforcement Learning (RL) for Combinatorial Optimization (CO)

benchmarks-acoustic-propagation • Rank 3.0 • Science 67%

Coupled model development for acoustic propagation through multilayer systems for particle-velocity sensors

pytorch-benchmark • Rank 11.9 • Science 57%

Easily benchmark PyTorch model FLOPs, latency, throughput, allocated gpu memory and energy consumption

hyperfine • Rank 14.9 • Science 54%

A command-line benchmarking tool

fastrag • Rank 14.7 • Science 54%

Efficient Retrieval Augmentation and Generation Framework

eval-suite • Rank 9.2 • Science 59%

[ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA, etc.

logpai • Rank 18.1 • Science 49%

A machine learning toolkit for log parsing [ICSE'19, DSN'16]

py-torchbenchmark • Rank 12.5 • Science 54%

TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.

@stdlib/bench-harness • Rank 11.1 • Science 54%

Benchmark harness.

matbench • Rank 14.5 • Science 49%

Matbench: Benchmarks for materials science property prediction

benchmarl • Rank 8.2 • Science 54%

BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.

h5bench • Rank 7.9 • Science 54%

A benchmark suite for measuring HDF5 performance.

evo • Rank 22.0 • Science 36%

Python package for the evaluation of odometry and SLAM

qcd • Rank 4.0 • Science 54%

Quantum Circuit Designer: A gymnasium-based set of environments for benchmarking reinforcement learning for quantum circuit design.

muld • Rank 3.8 • Science 54%

The Multitask Long Document Benchmark

xfinder • Rank 6.6 • Science 51%

[ICLR 2025] xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation

aptv2 • Rank 3.3 • Science 54%

The official repo for the extension of [NeurIPS'22] "APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking": https://github.com/pandorgan/APT-36K

springwebsite • Rank 3.2 • Science 54%

Website code of Spring benchmark

jreferral • Rank 3.2 • Science 54%

An open-source tool that recommends the most energy efficient JVM configuration for java software

@stdlib/utils-timeit • Rank 2.9 • Science 54%

Time a snippet.

@stdlib/bench • Rank 11.0 • Science 44%

Benchmark.

birdset • Rank 7.0 • Science 46%

A benchmark dataset collection for bird sound classification

https://github.com/csgillespie/benchmarkme • Rank 16.6 • Science 36%

Crowd sourced benchmarking

are-we-fast-yet • Rank 8.2 • Science 44%

Are We Fast Yet? Comparing Language Implementations with Objects, Closures, and Arrays

opencl-benchmark • Rank 5.5 • Science 44%

A small OpenCL benchmark program to measure peak GPU/CPU performance.

https://github.com/beuth-erdelt/benchmark-experiment-host-manager • Rank 9.9 • Science 39%

This python tool helps managing DBMS benchmarking experiments in a Kubernetes-based HPC cluster environment. It enables users to configure hardware / software setups for easily repeating tests over varying configurations.

https://github.com/bark-simulator/bark • Rank 15.4 • Science 33%

Open-Source Framework for Development, Simulation and Benchmarking of Behavior Planning Algorithms for Autonomous Driving

tax-retrieval-benchmark • Rank 0.7 • Science 44%

An implementation of the TaxRetrievalBenchmark task for the 🤗 Massive Text Embedding Benchmark (MTEB) framework.

https://github.com/bio-phys/mdbenchmark • Rank 10.6 • Science 33%

Quickly generate, start and analyze benchmarks for molecular dynamics simulations.

polybench • Rank 7.5 • Science 36%

Multivariate polynomial arithmetic benchmark tests.

https://github.com/google-deepmind/physics-iq-benchmark • Rank 6.9 • Science 36%

Benchmarking physical understanding in generative video models

leakdb • Rank 5.2 • Science 36%

LeakDB (Leakage Diagnosis Benchmark) is a realistic leakage dataset for water distribution networks. The dataset is comprised of a large number of artificially created but realistic leakage scenarios, on different water distribution networks, under varying conditions. A scoring algorithm in MATLAB code is provided to evaluate the results of different algorithms.

hdnom • Rank 14.5 • Science 26%

🔮 Benchmarking and visualization toolkit for penalized Cox models

https://github.com/cbg-ethz/bmi • Rank 4.8 • Science 33%

Mutual information estimators and benchmark

https://github.com/brucewlee/h-test • Rank 0.7 • Science 33%

[ACL 2024] Language Models Don't Learn the Physical Manifestation of Language

https://github.com/crowdstrike/cloud-resource-estimator • Rank 5.5 • Science 26%

Cloud deployment size calculation utilities

https://github.com/cdjellen/otbench • Rank 5.0 • Science 26%

Effective Benchmarks for Optical Turbulence Modeling

sceneflow_from_blender • Rank 2.8 • Science 28%

Get 3D motion vectors / scene flow directly from Blender

https://github.com/awadell1/pkgjogger.jl • Rank 4.2 • Science 26%

Take your packages for a jog!

spring_utils • Rank 1.4 • Science 28%

Additional utility code for the Spring dataset and benchmark

https://github.com/aim-uofa/geobench • Rank 4.8 • Science 23%

A toolbox for benchmarking SOTA discriminative and generative geometry estimation models.

https://github.com/lquenti/blackheap • Rank 1.6 • Science 26%

An blackbox approach to I/O modelling. (Migrated to Codeberg)

https://github.com/citiususc/blinkg • Rank 0.7 • Science 26%

BLINKG: Benchmark for LLM-Integrated Knowledge Graph Generation

https://github.com/avik-pal/deeplearningbenchmarks • Rank 3.3 • Science 23%

Benchmarks across Deep Learning Frameworks in Julia and Python

https://github.com/ai-forever/ruscode • Rank 2.1 • Science 23%

Official repository for RusCode benchmark dataset (NAACL 2025)

https://github.com/jurgisp/memory-maze • Rank 12.3 • Science 10%

Evaluating long-term memory of reinforcement learning algorithms

https://github.com/crate/tsperf • Rank 4.4 • Science 13%

TSPERF Time Series Database Benchmark Suite. Framework for evaluating and comparing the performance of time series databases, in the spirit of TimescaleDB's TSBS.

https://github.com/yegor256/plum • Rank 3.8 • Science 13%

Programming language ultimate metrics (PLUM) collected automatically from GitHub, Google Scholar, Twitter, etc.

pglib-opf • Rank 5.9 • Science 10%

Benchmarks for the Optimal Power Flow Problem

cellbench • Rank 5.6 • Science 10%

R package for benchmarking single cell analysis methods

https://github.com/aliireza/ddio-bench • Rank 5.2 • Science 10%

Reexamining Direct Cache Access to Optimize I/O Intensive Applications for Multi-hundred-gigabit Networks

https://github.com/ceed/benchmarks • Rank 5.2 • Science 10%

CEED Benchmarks

https://github.com/cvanaret/nonconvex_solver_comparison • Rank 1.9 • Science 13%

This repo collects results of nonlinear optimization solvers on standard benchmark problems

https://github.com/bblodfon/paad-survival-bench • Rank 1.8 • Science 13%

Benchmark survival ML models against a multimodal TCGA dataset

https://github.com/bblodfon/ml-course-2022 • Rank 0.7 • Science 13%

Benchmarking ML classification models on spam dataset

https://github.com/hyperledger-caliper/caliper-benchmarks • Science 13%

Sample benchmark files for Hyperledger Caliper https://wiki.hyperledger.org/display/caliper

hyperspectral-soilmoisture-dataset • Science 77%

Hyperspectral and soil-moisture data from a field campaign based on a soil sample. Karlsruhe (Germany), 2017.

fast_frechet-python • Science 44%

Comparison of different (fast) discrete Fréchet distance implementations in Python.

https://github.com/axect/scientific_bench • Science 26%

Benchmark some scientific computations for various languages & libraries

benchmark-privesc-linux • Science 54%

A comprehensive local Linux Privilege-Escalation Benchmark

variantbenchmarking • Science 57%

Pipeline to evaluate and validate the accuracy of variant calling methods in genomic research

leaderboard • Science 44%

You can find the most recent KGQA benchmark numbers from publications here.

sachau-2022-icesheet • Science 57%

maskedfacerepresentation • Science 39%

Masked face recognition focuses on identifying people using their facial features while they are wearing masks. We introduce benchmarks on face verification based on masked face images for the development of COVID-safe protocols in airports.

dpl • Science 44%

[NeurIPS 2023] Multi-fidelity hyperparameter optimization with deep power laws that achieves state-of-the-art results across diverse benchmarks.

benchmarks • Science 44%

A collection of micro benchmarks.

pauli-coloring-benchmark • Science 44%

Or "colouring" if you prefer 🎨

https://github.com/bethgelab/model-vs-human • Science 36%

Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)

hyphi-gym • Science 54%

A Gymnasium benchmark suite for evaluating the robustness and multi-task performance of reinforcement learning algorithms in various discrete and continuous environments.

chembench • Science 36%

How good are LLMs at chemistry?

posebench • Science 49%

Comprehensive benchmarking of protein-ligand structure prediction methods. (ICML 2024 AI4Science)

neteasecrowd-dataset • Science 54%

NetEaseCrowd dataset, a collection of data obtained from You Ling crowdsourcing platform, Fuxi AI Lab, NetEase.

https://github.com/alan-turing-institute/tcpdbench • Science 23%

The Turing Change Point Detection Benchmark: An Extensive Benchmark Evaluation of Change Point Detection Algorithms on real-world data

fingernat-ml • Science 49%

Data accompanying the manuscript on SIFts- and ML-based methods in Virtual Screening for RNA binding ligands.

stochastic-benchmark • Science 36%

Repository for Stochastic Optimization Solvers Benchmark code

benchmarks • Science 44%

World's complete programming language benchmark

small-object-detection-benchmark • Science 67%

icip2022 paper: sahi benchmark on visdrone and xview datasets using fcos, vfnet and tood detectors