Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Awesome-LLM-Long-Context-Modeling
Datasets & benchmarks📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥
git clone https://github.com/Xnhyacinth/Awesome-LLM-Long-Context-Modeling.git -
LongCite
Datasets & benchmarksLongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
git clone https://github.com/THUDM/LongCite.git -
LongBench
Datasets & benchmarksLongBench v2 and LongBench (ACL 25'&24')
git clone https://github.com/THUDM/LongBench.git -
NoLiMa
Datasets & benchmarksOfficial repository for "NoLiMa: Long-Context Evaluation Beyond Literal Matching"
git clone https://github.com/adobe-research/NoLiMa.git -
WritingBench
Datasets & benchmarksWritingBench: A Comprehensive Benchmark for Generative Writing
git clone https://github.com/X-PLUG/WritingBench.git -
LongBench
Datasets & benchmarksHugging Face dataset by zai-org
zai-org/LongBench -
Nemotron-Math-v2
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/Nemotron-Math-v2 -
CL-bench
Datasets & benchmarksHugging Face dataset by tencent
tencent/CL-bench -
LongWriter-6k
Datasets & benchmarksHugging Face dataset by zai-org
zai-org/LongWriter-6k -
UltraData-RL-2609
Datasets & benchmarksHugging Face dataset by openbmb
openbmb/UltraData-RL-2609 -
frames-benchmark
Datasets & benchmarksHugging Face dataset by google
google/frames-benchmark -
opencompass
Datasets & benchmarksOpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.
git clone https://github.com/open-compass/opencompass.git -
LongPage
Datasets & benchmarksHugging Face dataset by Pageshift-Entertainment
Pageshift-Entertainment/LongPage
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.