Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to research potential clients
-
llm-perf-leaderboard
Tools & appsHugging Face space by optimum
optimum/llm-perf-leaderboard -
open_llm_leaderboard
Tools & appsHugging Face space by open-llm-leaderboard
open-llm-leaderboard/open_llm_leaderboard -
open-ko-llm-leaderboard
Tools & appsHugging Face space by upstage
upstage/open-ko-llm-leaderboard -
hallucination-leaderboard
AI repositoriesLeaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents
git clone https://github.com/vectara/hallucination-leaderboard.git -
Berkeley-Function-Calling-Leaderboard
Datasets & benchmarksHugging Face dataset by gorilla-llm
gorilla-llm/Berkeley-Function-Calling-Leaderboard -
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.
git clone https://github.com/oolong-tea-2026/arena-ai-leaderboards.git -
RouterArena
Agents & frameworksRouterArena: An open framework for evaluating LLM routers with standardized datasets, metrics, an automated framework, and a live leaderboard.
git clone https://github.com/RouteWorks/RouterArena.git -
Awesome-LLM-Eval
Datasets & benchmarksAwesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs. 一个由工具、基准/数据、演示、排行榜和大模型等组成的精选列表,主要面向基础大模型评测,旨在探求生成式AI的技术边界.
git clone https://github.com/onejune2018/Awesome-LLM-Eval.git -
lora-speedrun
Datasets & benchmarksSpeedrunning LoRA fine-tuning: frozen task, frozen hardware, public wall-clock leaderboard. modded-nanogpt for fine-tuning.
git clone https://github.com/Saivineeth147/lora-speedrun.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 -
ClawProBench
Datasets & benchmarksClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.
git clone https://github.com/suyoumo/ClawProBench.git -
ds4-on-spark
Datasets & benchmarksEntrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark, and full continuous batch support
git clone https://github.com/Entrpi/ds4-on-spark.git -
FastEval
Datasets & benchmarksFast & more realistic evaluation of chat language models. Includes leaderboard.
git clone https://github.com/FastEval/FastEval.git -
confabulations
Datasets & benchmarksHallucinations (Confabulations) Document-Based Benchmark for RAG. Includes human-verified questions and answers.
git clone https://github.com/lechmazur/confabulations.git -
api-perf-analyzer
MCP serversCloudflare Workers MCP server: api-perf-analyzer
-
polymarket-paper-trader
Datasets & benchmarksPaper trading simulator for Polymarket
git clone https://github.com/agent-next/polymarket-paper-trader.git -
GPT-X3-150M
Modelstext generation model by AxiomicLabs · transformers
AxiomicLabs/GPT-X3-150M -
debate
Datasets & benchmarksAdversarial multi-turn benchmark for LLM debate quality, using side-swapped matchups and multi-model judging to rank models by judged debate performance.
git clone https://github.com/lechmazur/debate.git -
perf
MCP serversBenchmark, memory, Big O analysis for AI agents
@rog0x/mcp-perf-tools@1.0.2 -
perf-mcp
MCP serversFact-check and fix AI outputs. Hallucination detection, schema validation, auto-repair.
perf-mcp@0.1.1 -
evaluation-guidebook
Docs & tutorialsSharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!
git clone https://github.com/huggingface/evaluation-guidebook.git -
claude-opus-4-6-high leads Arena coding at 1535. Anthropic has held #1 for 280 days, but Z.ai.
-
leaderboard
Tools & appsHugging Face space by mteb
mteb/leaderboard -
The gap between Arena's #1 and #10 models fell from 148 points in Feb 2024 to 18. #10 now wins.
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.