InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. MobileWorld

    Datasets & benchmarks

    Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments (ACL 2026)

    Stale GitHub, Tongyi-MAI 300 ★Apache-2.0Updated 14 days ago

    git clone https://github.com/Tongyi-MAI/MobileWorld.git
  2. geobench

    Datasets & benchmarks

    GeoGuessr benchmark for language models

    Indexed GitHub, ccmdi 65 ★MITUpdated 4 days ago

    git clone https://github.com/ccmdi/geobench.git
  3. SciCode

    Datasets & benchmarks

    A benchmark that challenges language models to code solutions for scientific problems

    Stale GitHub, scicode-bench 246 ★Apache-2.0Updated 15 days ago

    git clone https://github.com/scicode-bench/SciCode.git
  4. ping_pong_bench

    Datasets & benchmarks

    A benchmark for role-playing language models

    Stale GitHub, IlyaGusev 122 ★Apache-2.0Updated 18 months ago

    git clone https://github.com/IlyaGusev/ping_pong_bench.git
  5. PawBench

    Datasets & benchmarks

    A benchmark for evaluating LLM × harness performance.

    Stale GitHub, agentscope-ai 118 ★Apache-2.0Updated 3 months ago

    git clone https://github.com/agentscope-ai/PawBench.git
  6. MMLU-CF

    Datasets & benchmarks

    A Contamination-free Multi-task Language Understanding Benchmark [Official, ACL 2025]

    Stale GitHub, microsoft 127 ★MITUpdated 18 months ago

    git clone https://github.com/microsoft/MMLU-CF.git
  7. minebench

    Datasets & benchmarks

    Minecraft-style voxel benchmark for comparing AI models (Arena + Sandbox)

    Indexed GitHub, Ammaar-Alam 343 ★MITUpdated 5 days ago

    git clone https://github.com/Ammaar-Alam/minebench.git
  8. BizFinBench

    Datasets & benchmarks

    A Business-Driven Real-World Financial Benchmark for Evaluating LLMs

    Stale GitHub, HiThink-Research 169 ★Updated 6 months ago

    git clone https://github.com/HiThink-Research/BizFinBench.git
  9. OSWorld

    Datasets & benchmarks

    [NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

    Indexed GitHub, xlang-ai 3,262 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/xlang-ai/OSWorld.git
  10. o11y-bench

    Datasets & benchmarks

    Open benchmark on observability tasks built on Harbor

    Indexed GitHub, grafana 80 ★AGPL-3.0Updated yesterday

    git clone https://github.com/grafana/o11y-bench.git
  11. AICGSecEval

    Datasets & benchmarks

    A.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.

    Stale GitHub, Tencent 664 ★Custom licence (see repository)Updated 5 months ago

    git clone https://github.com/Tencent/AICGSecEval.git
  12. LoopArena

    Datasets & benchmarks

    Benchmarking models as runtime Controllers for Loop Engineering

    Stale GitHub, AMAP-ML 151 ★Apache-2.0Updated 33 days ago

    git clone https://github.com/AMAP-ML/LoopArena.git
  13. chembench

    Datasets & benchmarks

    How good are LLMs at chemistry?

    Stale GitHub, lamalab-org 147 ★MITUpdated 9 months ago

    git clone https://github.com/lamalab-org/chembench.git
  14. LLM-Agent-Benchmark-List

    Datasets & benchmarks

    A banchmark list for evaluation of large language models.

    Stale GitHub, zhangxjohn 173 ★Apache-2.0Updated 12 days ago

    git clone https://github.com/zhangxjohn/LLM-Agent-Benchmark-List.git
  15. turnkeyml

    Datasets & benchmarks

    No-code CLI designed for accelerating ONNX workflows

    Stale GitHub, onnx 247 ★Apache-2.0Updated 4 months ago

    git clone https://github.com/onnx/turnkeyml.git
  16. LLM-RGB

    Datasets & benchmarks

    LLM Reasoning and Generation Benchmark. Evaluate LLMs in complex scenarios systematically.

    Stale GitHub, babelcloud 165 ★MITUpdated 18 months ago

    git clone https://github.com/babelcloud/LLM-RGB.git
  17. ParseBench

    Datasets & benchmarks

    ParseBench - A Document Parsing Benchmark for AI Agents

    Indexed GitHub, run-llama 640 ★Apache-2.0Updated yesterday

    git clone https://github.com/run-llama/ParseBench.git
  18. ClawProBench

    Datasets & benchmarks

    ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.

    Stale GitHub, suyoumo 825 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/suyoumo/ClawProBench.git
  19. WritingBench

    Datasets & benchmarks

    WritingBench: A Comprehensive Benchmark for Generative Writing

    Stale GitHub, X-PLUG 202 ★Apache-2.0Updated 11 months ago

    git clone https://github.com/X-PLUG/WritingBench.git
  20. OneMillion-Bench

    Datasets & benchmarks

    [NeurIPS 2026] $OneMillion-Bench: How Far are Language Agents from Human Experts?

    Stale GitHub, humanlaya 55 ★Apache-2.0Updated 28 days ago

    git clone https://github.com/humanlaya/OneMillion-Bench.git
  21. Awesome-LLM-Long-Context-Modeling

    Datasets & benchmarks

    📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

    Indexed GitHub, Xnhyacinth 2,192 ★MITUpdated 4 days ago

    git clone https://github.com/Xnhyacinth/Awesome-LLM-Long-Context-Modeling.git
  22. aa-agentperf-local

    Datasets & benchmarks

    Benchmark local LLM serving by replaying real agent trajectories

    Stale GitHub, ArtificialAnalysis 105 ★Apache-2.0Updated 32 days ago

    git clone https://github.com/ArtificialAnalysis/aa-agentperf-local.git
  23. PhysGym

    Datasets & benchmarks

    A benchmark suite for evaluating LLM-based interactive scientific reasoning.

    Indexed GitHub, principia-ai 103 ★MITUpdated 4 days ago

    git clone https://github.com/principia-ai/PhysGym.git
  24. ollama-benchmark

    Datasets & benchmarks

    Ollama based Benchmark with detail I/O token per second. Python with Deepseek R1 example.

    Stale GitHub, LarHope 174 ★MITUpdated 7 months ago

    git clone https://github.com/LarHope/ollama-benchmark.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.