Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
UltraX-Preview
Datasets & benchmarksHugging Face dataset by openbmb
openbmb/UltraX-Preview -
ToolScale
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/ToolScale -
UltraData-Code
Datasets & benchmarksHugging Face dataset by openbmb
openbmb/UltraData-Code -
Ultra-FineWeb-L1
Datasets & benchmarksHugging Face dataset by openbmb
openbmb/Ultra-FineWeb-L1 -
monet
Datasets & benchmarksHugging Face dataset by jasperai
jasperai/monet -
Glyd
Datasets & benchmarksLossless AI compression: 33% less GPU memory, bit for bit.
git clone https://github.com/surya-koritala/Glyd.git -
humanities_data_benchmark
Datasets & benchmarksLLM Benchmark Suite for Humanities Data
git clone https://github.com/RISE-UNIBAS/humanities_data_benchmark.git -
Nemotron-Math-Proofs-v1
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/Nemotron-Math-Proofs-v1 -
10k_prompts_ranked
Datasets & benchmarksHugging Face dataset by data-is-better-together
data-is-better-together/10k_prompts_ranked -
rotten_tomatoes
Datasets & benchmarksHugging Face dataset by cornell-movie-review-data
cornell-movie-review-data/rotten_tomatoes -
Zero-To-CAD-1m
Datasets & benchmarksHugging Face dataset by ADSKAILab
ADSKAILab/Zero-To-CAD-1m -
Static-to-Dynamic-LLMEval
Datasets & benchmarksThe official GitHub repository of the paper "Recent advances in large language model benchmarks against data contamination: From static to dynamic evaluation"
git clone https://github.com/SeekingDream/Static-to-Dynamic-LLMEval.git -
synthetic-dataset-1m-dalle3-high-quality-captions
Datasets & benchmarksHugging Face dataset by ProGamerGov
ProGamerGov/synthetic-dataset-1m-dalle3-high-quality-captions -
teor
Datasets & benchmarksBenchmark aberto de LLMs para o processo legislativo brasileiro
git clone https://github.com/como-votam/teor.git -
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 -
DyCodeEval
Datasets & benchmarksOfficial repository of the ICML2025 paper “Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination”
git clone https://github.com/SeekingDream/DyCodeEval.git -
TraderHarness
Datasets & benchmarks面向 LLM 交易 Agent 的抗污染回测、确定性回放与训练轨迹生成,支持 A 股研究|Leakage-resistant backtesting, deterministic replay & training trajectory generation for LLM trading agents, with A-share data
git clone https://github.com/HephaestLab/TraderHarness.git -
deepmark
Datasets & benchmarksDeepmark AI enables a unique testing environment for language models (LLM) assessment on task-specific metrics and on your own data so your GenAI-powered solution has predictable and reliable performance.
git clone https://github.com/IngestAI/deepmark.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.