InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. Awesome-Scientific-LLM-Benchmarks

    Datasets & benchmarks

    A curated, accuracy-first list of benchmarks for evaluating LLMs on scientific reasoning and discovery — math, physics, chemistry, materials, biology, and agentic science.

    Stale GitHub, subinium 42 ★MITUpdated 14 days ago

    git clone https://github.com/subinium/Awesome-Scientific-LLM-Benchmarks.git
  2. Multi-User-LLM-Agent

    Datasets & benchmarks

    Official code for the paper: "Multi-User Large Language Model Agents"

    Stale GitHub, Kordi-AI 39 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/Kordi-AI/Multi-User-LLM-Agent.git
  3. debate

    Datasets & benchmarks

    Adversarial multi-turn benchmark for LLM debate quality, using side-swapped matchups and multi-model judging to rank models by judged debate performance.

    Stale GitHub, lechmazur 38 ★Updated 21 days ago

    git clone https://github.com/lechmazur/debate.git
  4. explicit-edit-benchmark

    Datasets & benchmarks

    Benchmark coding agents and agent harnesses on 226 deterministic file-editing tasks with byte-exact verification and a public leaderboard.

    Stale GitHub, alexshpunt 38 ★MITUpdated 7 days ago

    git clone https://github.com/alexshpunt/explicit-edit-benchmark.git
  5. qwen38-strix-halo-harness

    Datasets & benchmarks

    AI coding agent harness for any hardware, local or cloud (OpenAI-compatible engines). Tuned for AMD Strix Halo: Qwen3.8 125B on the iGPU, NPU side-jobs, crash recovery, logged benchmarks.

    Stale GitHub, aic0d3r 38 ★MITUpdated 8 days ago

    git clone https://github.com/aic0d3r/qwen38-strix-halo-harness.git
  6. gamebot

    Datasets & benchmarks

    [ACL 2025] GAMEBoT: Transparent Assessment of LLM Reasoning in Games

    Stale GitHub, Visual-AI 36 ★Updated 10 days ago

    git clone https://github.com/Visual-AI/gamebot.git
  7. lasagna

    Datasets & benchmarks

    Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.

    Indexed GitHub, dolev31 35 ★Apache-2.0Updated yesterday

    git clone https://github.com/dolev31/lasagna.git
  8. agent-duel

    Datasets & benchmarks

    Blinded battles between coding agents: two agents, one prompt, you pick the winner. Desktop app, runs locally.

    Stale GitHub, bottomless 35 ★Custom licence (see repository)Updated 5 days ago

    git clone https://github.com/bottomless/agent-duel.git
  9. self-bench

    Datasets & benchmarks

    Benchmark coding agents and models on your own repository with private Harbor-formatted evals built from its merged pull requests.

    Indexed GitHub, mupt-ai 34 ★MITUpdated today

    git clone https://github.com/mupt-ai/self-bench.git
  10. xorcise

    Datasets & benchmarks

    Run cyber-AI agents against real missions in isolated environments. Record everything as OpenTelemetry evidence. Grade the evidence, not the claim.

    Stale GitHub, xorcise-ai 33 ★Custom licence (see repository)Updated 17 days ago

    git clone https://github.com/xorcise-ai/xorcise.git
  11. humanities_data_benchmark

    Datasets & benchmarks

    LLM Benchmark Suite for Humanities Data

    Stale GitHub, RISE-UNIBAS 32 ★GPL-3.0Updated 12 days ago

    git clone https://github.com/RISE-UNIBAS/humanities_data_benchmark.git
  12. teor

    Datasets & benchmarks

    Benchmark aberto de LLMs para o processo legislativo brasileiro

    Stale GitHub, como-votam 30 ★Apache-2.0Updated 18 days ago

    git clone https://github.com/como-votam/teor.git
  13. llm-value-rankings

    Datasets & benchmarks

    Daily LLM value rankings - compare 300+ models by intelligence, speed and price. OpenRouter + Artificial Analysis. 大模型性价比排行榜

    Indexed GitHub, yyh-001 30 ★MITUpdated yesterday

    git clone https://github.com/yyh-001/llm-value-rankings.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.