Havuz

Self-hosted, one-tab workbench for the whole training lifecycle: build Character/Concept/Style datasets (generate, scrape, or triage a big d

A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence

Open-source benchmark for browser AI agents on daily tasks.

SkillCorpus, dağınık SKILL.md dosyalarını agent'lar için seçilmiş, aranabilir skill corpus'larına dönüştüren ve retrieval ile evaluation araçları sunan açık kaynak bir altyapıdır.

Neden yükseliyor · Agent'lar için paylaşılan ve göreve göre seçilen skill katmanına ilgi var; repo kısa sürede 667 yıldıza ulaşmış ve son 28 günde 9 commit ile 3 farklı yazar katkı vermiş. README ayrıca birden fazla benchmark'ta iyileşme bildiriyor; bu sonuçları bağımsız olarak doğrulayamıyorum.

Custom APRL machine-learning algorithm + a curated ML knowledge base of 923 papers, lectures, and explainers. NumPy classifier/regressor, te

Real-event-anchored benchmark for detecting AI-generated videos in real-world crisis settings.

CrowdGPT is an opensource framework that aims to train AI without any datacenters

Open, evidence-backed infrastructure for tracking university AI policies worldwide.

Somali NLP Corpus is an open, high-quality Somali text corpus designed to support research and development in Natural Language Processing (N

Open, structured corpus of US primary law: 2M+ sections of state statutory codes, the US Code, and state constitutions, plus the ingestion p

Benchmark self-evolving Agent upon realistic large-scale file workspaces

Open, correctly-licensed JLPT N5–N1 dataset — vocabulary, kanji & example sentences as JSON, CSV & SQLite.

ICML 2026 benchmark and MechVL models for multimodal understanding of mechanical engineering drawings.

[ECCV 2026] AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World

Benchmarking Agents on Real-World Terminal Tasks

A zero-dependency Python module for inspecting and converting coding-agent session files (.jsonl) — Claude Code, Codex, and Pi — into the me

A tiny language model that talks like a house cat named Miso.

Open benchmark datasets republished in stressed form to evaluate ML/LLM robustness. Curated by Santander AI Lab.

Free, open dataset of car makes → models → generations → engine specs (164 makes, 30k+ engines). JSON/CSV/SQLite, ODbL. Auto-updated weekly.

中国法律法规与案例结构化语料库：446 部法律/司法解释逐条 JSON（含效力状态）+ 278 指导性案例 + 445 公报案例，CC0

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining (ICML2026)

Open geographic data for Algeria: 30 npm packages, 83,000+ records, plus the trilingual interactive atlas at geoalgeria.com. Wilayas, commun

1,017 system prompts from real AI products, audited span by span against the eight AISPA assurance dimensions

This dataset provides metadata, official statistics, and official play-by-play annotations for full-length NBA game videos available on YouT

SomNLP-Translate is an open, high-quality English–Somali parallel dataset designed to support research and development in machine translatio

Open vehicle data: 19,282 models, 933 makes, 6 kinds (cars, motorcycles, mopeds, vans, trucks, buses) reconciled from official registers of

A BNCC como dados abertos e verificados: 1.721 aprendizagens em JSON, SQLite e CSV, com proveniência por registro e pipeline de extração rep

Scenarios and tasks for evaluating AI agents on real-world AWS automation tasks. Use the aws-bench framework (https://github.com/aws-bench/a

crawl4ai for video & audio — turn any YouTube video, podcast, or recording into clean timestamped markdown, or a verified TTS/STT training d

Live Benchmark for long Horizon tool using Agentic Systems

Easy access to speech data across 142 African languages for training TTS and ASR models.

chew through any source into clean datasets! a fast ingestion, RAG & fine-tuning toolkit

Academic Data Scraper para extração massiva de metadados e abstracts (Scholar/Scielo/arXiv). Otimizado para alta performance e baixo consumo

Benchmark for repository-level code understanding: 500 open-ended questions from real GitHub Discussions across 50 repositories, graded by a

An open-source, automated historical dataset of F1 Fantasy statistics.