Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
MiroVerse-v0.1
Datasets & benchmarksHugging Face dataset by miromind-ai
miromind-ai/MiroVerse-v0.1 -
mobilegym
Datasets & benchmarks[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training
git clone https://github.com/Purewhiter/mobilegym.git -
minebench
Datasets & benchmarksMinecraft-style voxel benchmark for comparing AI models (Arena + Sandbox)
git clone https://github.com/Ammaar-Alam/minebench.git -
NuminaMath-TIR
Datasets & benchmarksHugging Face dataset by AI-MO
AI-MO/NuminaMath-TIR -
ai-model-world
Datasets & benchmarksAI 大模型世界,把 556 个大模型拟人化成像素小人的可视化站点。进来就能看到此刻谁最聪明、谁最会写代码、谁最便宜、谁刚发布,往下是国内与国外分区的厂商广场、完整的发布时间线和多维排行榜。搜索认模型名、厂商和能力,输入「多模态」会直接列出全部多模态模型。数据取自 Epoch AI、models.dev、LiveBench 与 Hugging Face,每小时自动同步,所有文案由真实数据生成,不调用任何 LLM。Next.js 静态导出,零后端。
git clone https://github.com/liyupi/ai-model-world.git -
Bitext-customer-support-llm-chatbot-training-dataset
Datasets & benchmarksHugging Face dataset by bitext
bitext/Bitext-customer-support-llm-chatbot-training-dataset -
WebsiteBench
Datasets & benchmarksCan AI agents rebuild websites through browser exploration?
git clone https://github.com/TIGER-AI-Lab/WebsiteBench.git -
gpt4all-j-prompt-generations
Datasets & benchmarksHugging Face dataset by nomic-ai
nomic-ai/gpt4all-j-prompt-generations -
meta-agents-research-environments
Datasets & benchmarksMeta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environments where agents must adapt their strategies as new information becomes available, mirroring real-world challenges.
git clone https://github.com/facebookresearch/meta-agents-research-environments.git -
tulu-3-sft-mixture
Datasets & benchmarksHugging Face dataset by allenai
allenai/tulu-3-sft-mixture -
SciCode
Datasets & benchmarksA benchmark that challenges language models to code solutions for scientific problems
git clone https://github.com/scicode-bench/SciCode.git -
Finance-Instruct-500k
Datasets & benchmarksHugging Face dataset by Josephgflowers
Josephgflowers/Finance-Instruct-500k -
Awesome-AI4AI
Datasets & benchmarksUpdated weekly — until humanity achieves AI4AI. 1148 curated papers across Benchmarks, Harness Design, and Model Design — from long-horizon agents to recursive self-improvement. Citation rankings, GitHub stars, and source-verified weekly news.
git clone https://github.com/KaiWU5/Awesome-AI4AI.git -
polymarket-paper-trader
Datasets & benchmarksPaper trading simulator for Polymarket
git clone https://github.com/agent-next/polymarket-paper-trader.git -
Sky-T1_data_17k
Datasets & benchmarksHugging Face dataset by NovaSky-AI
NovaSky-AI/Sky-T1_data_17k -
AutoMathText
Datasets & benchmarksHugging Face dataset by math-ai
math-ai/AutoMathText -
synthetic-healthcare-admissions
Datasets & benchmarksHugging Face dataset by strova-ai
strova-ai/synthetic-healthcare-admissions -
swe-sweep
Datasets & benchmarksHow many bugs can LMs find & fix in large codebases?
git clone https://github.com/facebookresearch/swe-sweep.git -
NuminaMath-1.5
Datasets & benchmarksHugging Face dataset by AI-MO
AI-MO/NuminaMath-1.5 -
computer-use-large
Datasets & benchmarksHugging Face dataset by markov-ai
markov-ai/computer-use-large -
tiny-textbooks
Datasets & benchmarksHugging Face dataset by nampdn-ai
nampdn-ai/tiny-textbooks -
CoT-Collection
Datasets & benchmarksHugging Face dataset by kaist-ai
kaist-ai/CoT-Collection -
PKU-SafeRLHF
Datasets & benchmarksHugging Face dataset by PKU-Alignment
PKU-Alignment/PKU-SafeRLHF -
Simreal-MLBench
Datasets & benchmarks[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluation.
git clone https://github.com/Simreal-AI/Simreal-MLBench.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.