SkillRank

AI benchmark for builders

Rank the models & agents your product actually ships.

SkillRank blends editorial judgment with verified daily GitHub signals, practical guides, and transparent methodology—so you can compare chat, vision, video, coding, and RAG stacks without spreadsheet chaos.

  • 111+

    Models

  • 6

    Categories

  • Nightly

    Refresh

Verified index

Tracked surface

111

Daily crawler coverage across model profiles, agent tools, and verified GitHub-backed entries.

Trust layer

Clear source boundaries for daily AI rankings.

SkillRank separates editorial model profiles from GitHub-verified repository signals. Daily automation records history snapshots when a public source can be checked, and pages link to methodology instead of stretching claims beyond the data.

Data statusEditorial policyMethodology

56

Verified repos

Checked through daily source verification.

1947

History points

Recorded snapshots, not simulated trends.

20

Editorial pages

Guides and comparisons written for decisions.

AI Intelligence Dashboard

Daily market signals, source checks, and editorial context.

Updated 2026-06-20. The dashboard turns crawler output into a compact control room for model movement, coding-agent attention, RAG signals, and verified open-source projects.

Open briefingsSource status

Crawler

Tools and skills refresh from the daily automation run.

Verification

115 rows are eligible for evidence-backed briefing inputs.

Briefing

Movement mode until enough snapshots prove weekly movement.

Verified inputs

115

Live

GitHub-backed rows with consistent source evidence.

History points

1947

Live

Recorded snapshots that power charts and weekly movement.

Coding pulse

11

Live

Coding models and verified repositories in the latest briefing.

RAG pulse

11

Live

Embedding, retrieval, and knowledge workflow signals.

Open-source watchlist

8 projects
ECCJavaGuidesuperpowersclaw-codelangchain

Category hubs

Start with the AI category, then choose the tool.

Each hub connects rankings, verified repositories, daily briefing signals, guides, and comparison pages.

All category hubs

Frontier

Frontier Models

A research hub for flagship reasoning, multimodal, and general-purpose AI models that product teams compare before standardizing a platform.

11

Entries

1

Signals

Coding

Coding Agents

A hub for AI coding agents, IDE copilots, terminal agents, and repository automation workflows with rollout and review guidance.

0

Entries

6

Signals

RAG

RAG Tools

A practical hub for embedding models, retrieval systems, vector search, reranking, document agents, and grounded answer evaluation.

5

Entries

6

Signals

Media

AI Video and Media

A hub for image and video generation tools, creative model workflows, production review, brand controls, and media rights checks.

12

Entries

6

Signals

Open source

Open-Source Agents

A hub for open-source agent frameworks, workflow builders, orchestration libraries, and repository-backed AI automation projects.

12

Entries

6

Signals

Decision hub

Learn the workflow, compare the options, then use the ranking.

The homepage now gives readers a path: practical guides for evaluation, comparison pages for tradeoffs, and the leaderboard for the final shortlist.

Guides

Frameworks that make model selection repeatable

Original playbooks for product, engineering, security, retrieval, media, and operations teams.

All guides
Model strategy9 min

AI Model Selection Framework for Product Teams

A practical framework for choosing chat, reasoning, multimodal, coding, and retrieval models without relying on launch hype.

Coding agents10 min

Coding Agent Rollout Playbook

How to introduce Claude Code, Cursor, Codex-style agents, Copilot, and open-source coding repos without weakening engineering review.

Retrieval8 min

RAG Evaluation Checklist

A grounded checklist for choosing embedding models, retrieval pipelines, rerankers, and document-agent workflows.

Compare

Focused tradeoff pages for real buying decisions

Side-by-side pages explain when to choose one model, platform, or agent workflow over another.

All comparisons
Frontier reasoningUpdated 2026-06-04

GPT-5.5 vs Claude Opus for Professional Work

A practical comparison of GPT-5.5 and Claude Opus for research, coding, long documents, agentic workflows, and enterprise evaluation.

Coding agentsUpdated 2026-06-04

Claude Code vs Cursor

Compare Claude Code and Cursor for repository work, IDE assistance, refactoring, code review, team rollout, and daily engineering workflows.

Platform choiceUpdated 2026-06-04

OpenAI vs Gemini for Product Teams

How product teams should compare OpenAI and Google Gemini for chat, multimodal apps, workflow automation, enterprise deployment, and cost control.

Ranking preview

Featured models

Start with the strongest cross-category picks, then move into the full board for category-specific shortlists.

Leaderboard

Full ranking

Filter by model category and open any profile for source notes, fit guidance, strengths, weaknesses, and trend snapshots.

Featured today

Daily Skill Picks

Daily discovery set built from verified skill and agent repositories in the Claude Code & OpenClaw catalog (same pool as /skills).

Rotation for Jun 21, 2026 (UTC)

codingClaude Code
CLIProxyAPI

Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.5, Grok 4.3, Claude model throug…

SourceSkill detail
codingClaude Code
oh-my-openagent

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

SourceSkill detail
codingClaude Code
caveman

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

SourceSkill detail
automationClaude Code
codegraph

Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

SourceSkill detail