Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
open_llm_leaderboard
Tools & appsHugging Face space by open-llm-leaderboard
open-llm-leaderboard/open_llm_leaderboard -
UGI-Leaderboard
Tools & appsHugging Face space by DontPlanToEnd
DontPlanToEnd/UGI-Leaderboard -
phi-4
Modelstext generation model by microsoft · transformers
microsoft/phi-4 -
VibeThinker-3B
Modelstext generation model by WeiboAI · transformers
WeiboAI/VibeThinker-3B -
Phi-4-reasoning-plus
Modelstext generation model by microsoft · transformers
microsoft/Phi-4-reasoning-plus -
gsm8k
Datasets & benchmarksHugging Face dataset by openai
openai/gsm8k -
GenPark Safe Eval Expression AST Sandbox
MCP serversZero-dependency AST safe mathematical and boolean expression evaluator and validator
https://github.com/Alpha-Park/genpark-safe-eval-expression-ast-sandbox-skill/releases/download/v1.0.1/genpark-safe-eval-expression-ast-sandbox-skill-v1.0.1.mcpb -
MathModelAgent
AI repositories🤖📐专为数学建模设计的 Agent & skills ,自动完成数学建模,生成一份完整的可以直接提交的论文。 An Agent Designed for Mathematical Modeling ,Automatically complete mathmodel and generate a complete paper ready for submission.
git clone https://github.com/jihe520/MathModelAgent.git -
phoenix
PromptsAI Observability & Evaluation
git clone https://github.com/Arize-ai/phoenix.git -
Qwen3.8-27B
Modelsimage text to text model by Qwen · transformers
Qwen/Qwen3.8-27B -
MetaMathQA
Datasets & benchmarksHugging Face dataset by meta-math
meta-math/MetaMathQA -
DeepSeek-Math-V2
Modelstext generation model by deepseek-ai · transformers
deepseek-ai/DeepSeek-Math-V2 -
sam3
Modelsmask generation model by facebook · transformers
facebook/sam3 -
math-modeling-skill
Skills数学建模技能 - 面向 CUMCM、MCM/ICM 等数学建模竞赛的三阶段工作流:建模分析、Python/MATLAB 编程与 DOCX 论文生成。包含丰富的算法资源库(优化/预测/评价/图论/机器学习等)、角色指导文档、论文模板和实用工具脚本
git clone https://github.com/XiaoMaColtAI/math-modeling-skill.git -
orca-math-word-problems-200k
Datasets & benchmarksHugging Face dataset by microsoft
microsoft/orca-math-word-problems-200k -
agent-skills-eval
SkillsA test runner for agentskills.io-style AI agent skills
git clone https://github.com/darkrishabh/agent-skills-eval.git -
open-web-math
Datasets & benchmarksHugging Face dataset by open-web-math
open-web-math/open-web-math -
DeepSeek-R1
Modelstext generation model by deepseek-ai · transformers
deepseek-ai/DeepSeek-R1 -
UltraData-Math
Datasets & benchmarksHugging Face dataset by openbmb
openbmb/UltraData-Math -
Mixtral-8x7B-Instruct-v0.1
Modelsmodel by mistralai · vllm
mistralai/Mixtral-8x7B-Instruct-v0.1 -
OpenR1-Math-220k
Datasets & benchmarksHugging Face dataset by open-r1
open-r1/OpenR1-Math-220k -
MathInstruct
Datasets & benchmarksHugging Face dataset by TIGER-Lab
TIGER-Lab/MathInstruct -
trulens
Agents & frameworksEvaluation and Tracking for LLM Experiments and AI Agents
git clone https://github.com/truera/trulens.git -
DeepSeek-V4-Pro
Modelstext generation model by deepseek-ai · transformers
deepseek-ai/DeepSeek-V4-Pro
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.