Agents Directory
SkillsRankingsAgents
CategoriesModelsBenchmarksCompareAgent LeaderboardSkillsRankingsAgentsAbout
New

Work in progress: Agents Directory has just launched. Stay tuned, more content is on the way.

Discover and compare AI agents, skills, models & benchmarks

 
SkillsRankingsModels

Rankings

Top models

By AgentsDirectory Index

1Claude
Claude Fable 5

100
2Claude
Claude Opus 4.8

97.3
3OpenAI
GPT-5.5

97.2
4OpenAI
GPT-5.4

90.2
5Claude
Claude Opus 4.7

89.7
View all

Benchmark leaders

Artificial Analysis Intelligence Index logo
Artificial Analysis Intelligence Index
ClaudeClaude Fable 5

59.9
SWE-bench Verified logo
SWE-bench Verified
ClaudeClaude Fable 5

95%
DeepSWE logo
DeepSWE
OpenAIGPT-5.5

70%
FrontierCode Main logo
FrontierCode Main
ClaudeClaude Fable 5

46.3%
Cursor
CursorBench 3.1
ClaudeClaude Fable 5

72.9%
View all

Top agents

Hermes logo
Hermes

Claude Code logo
Claude Code

Codex logo
Codex

OpenClaw logo
OpenClaw

View all

By agent

All agents
Hermes logo

Hermes

Everything for the Hermes agent: skills, integrations, self-hosting, and the best models to run it on.
117 capabilities
Claude Code logo

Claude Code

Extend Anthropic's Claude Code with skills, plugins, MCP servers, and workflows, plus guides for installation, setup, and integrations.
122 capabilities
Codex logo

Codex

Supercharge OpenAI's Codex agent with reusable skills, MCP servers, and integrations.
122 capabilities
OpenClaw logo

OpenClaw

Skills, personas, and workflows for the OpenClaw operator agent.
117 capabilities

By category

All categories
Cloud Infrastructure

23
Productivity

17
Developer Tools

18
AI Development

9
Document Processing

8
Image & Video

10
Communication

10
DevOps

7

Learn

All guides

GPT-5.6 Sol, Terra and Luna benchmark results

GPT-5.6 Sol leads OpenAI's new family, while Terra and Luna target lower costs. Here are the independent and official benchmark results that matter.
Jul 10, 2026

Grok 4.5 benchmarks: frontier coding at a lower price

Grok 4.5 reaches 54 on the Artificial Analysis Intelligence Index and stays close to the leading coding models while using fewer tokens.
Jul 8, 2026

Z.ai launches GLM-5.2: 1M context, Coding Plan only, API to follow

GLM-5.2 is live on every GLM Coding Plan tier with a usable 1M-token context and High and Max effort levels. No standalone API yet, no open weights yet, and no benchmarks at launch. Here is what is actually confirmed.
Jun 15, 2026

Find the right skill for your agent

Browse skills, plugins, MCP servers, and workflows for Claude Code, Codex, Hermes & OpenClaw, all compared, ranked, and ready to install.

Browse SkillsView Rankings
Browse:SkillsRankingsModelsBenchmarksProvidersAgentsAgent LeaderboardCompareCategories
Quick Links:AboutBlog

© 2026 Agents Directory

104+ skills