InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. AI_Diplomacy

    Datasets & benchmarks

    Frontier Models playing the board game Diplomacy.

    Stale GitHub, GoodStartLabs 708 ★Custom licence (see repository)Updated 5 months ago

    git clone https://github.com/GoodStartLabs/AI_Diplomacy.git
  2. tau2-bench

    Datasets & benchmarks

    τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

    Indexed GitHub, sierra-research 2,442 ★MITUpdated 6 days ago

    git clone https://github.com/sierra-research/tau2-bench.git
  3. TheAgentCompany

    Datasets & benchmarks

    An agent benchmark with tasks in a simulated software company.

    Stale GitHub, TheAgentCompany 795 ★MITUpdated 12 months ago

    git clone https://github.com/TheAgentCompany/TheAgentCompany.git
  4. MedXpertQA

    Datasets & benchmarks

    [ICML 2025] MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding

    Stale GitHub, TsinghuaC3I 182 ★MITUpdated 2 months ago

    git clone https://github.com/TsinghuaC3I/MedXpertQA.git
  5. SciCode

    Datasets & benchmarks

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

    Stale GitHub, scicode-bench 246 ★Apache-2.0Updated 14 days ago

    git clone https://github.com/scicode-bench/SciCode.git
  6. o11y-bench

    Datasets & benchmarks

    Open benchmark on observability tasks built on Harbor

    Indexed GitHub, grafana 80 ★AGPL-3.0Updated today

    git clone https://github.com/grafana/o11y-bench.git
  7. NoLiMa

    Datasets & benchmarks

    Official repository for "NoLiMa: Long-Context Evaluation Beyond Literal Matching"

    Stale GitHub, adobe-research 205 ★Custom licence (see repository)Updated 16 months ago

    git clone https://github.com/adobe-research/NoLiMa.git
  8. arena-ai-leaderboards

    Datasets & benchmarks

    📊 Daily auto-updated snapshots of all Arena AI (LMSYS Chatbot Arena) leaderboards — LLM, Vision, Code, Video, Image & more. Structured JSON with historical tracking.

    Indexed GitHub, oolong-tea-2026 42 ★MITUpdated yesterday

    git clone https://github.com/oolong-tea-2026/arena-ai-leaderboards.git
  9. 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
  10. GDPevo

    Datasets & benchmarks

    A Benchmark for Evaluating Agent Self-Evolution on Real Business Tasks

    Stale GitHub, Prism-Shadow 119 ★Apache-2.0Updated 18 days ago

    git clone https://github.com/Prism-Shadow/GDPevo.git
  11. ChinaTravel

    Datasets & benchmarks

    ChinaTravel: A Real-World Benchmark for Language Agents in Chinese Travel Planning

    Stale GitHub, LAMDA-NeSy 133 ★MITUpdated 2 months ago

    git clone https://github.com/LAMDA-NeSy/ChinaTravel.git
  12. HaluMem

    Datasets & benchmarks

    HaluMem is the first operation level hallucination evaluation benchmark tailored to agent memory systems.

    Stale GitHub, MemTensor 178 ★Custom licence (see repository)Updated 19 days ago

    git clone https://github.com/MemTensor/HaluMem.git
  13. NIMStats

    Datasets & benchmarks

    📊 Automated hourly benchmarks for 20+ NVIDIA NIM models — interactive dashboard, zero infra, self-hostable. Open-source & community-driven.

    Indexed GitHub, MauroDruwel 57 ★Updated today

    git clone https://github.com/MauroDruwel/NIMStats.git
  14. nautilus-compass

    Datasets & benchmarks

    Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform

    Indexed GitHub, chunxiaoxx 1,258 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/chunxiaoxx/nautilus-compass.git
  15. VibeSearchBench

    Datasets & benchmarks

    🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure, scored by verifiable schema-free knowledge-graph evaluation. No vibes, just triplet F1.

    Stale GitHub, VibeBench 112 ★MITUpdated 5 months ago

    git clone https://github.com/VibeBench/VibeSearchBench.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.