AI tool comparison
Structured Output Benchmark vs Skills (mattpocock)
Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.
Developer Tools
Structured Output Benchmark
The benchmark that tests whether LLMs get JSON values right, not just syntax
75%
Panel ship
—
Community
Free
Entry
Interfaze's Structured Output Benchmark (SOB) exposes a gap that has been quietly breaking production AI pipelines: models can produce syntactically valid JSON while getting the actual values wrong. SOB measures value accuracy across 21 models using 5,000 text passages, 209 OCR documents, and 115 meeting transcripts — scoring each on seven metrics including value accuracy, faithfulness (grounding vs. hallucination), type safety, and perfect-response rate. The benchmark reveals some sobering findings. Even top models like GPT-5.4 and Claude Sonnet 4.6 achieve ~83% on text but drop to 67% on images and only 23.7% on audio. No single model dominates all modalities — GPT-5.4, GLM-4.7, Qwen3.5-35B, and Gemini 2.5 Flash cluster within one point of each other on text. Perfect response rates (all seven metrics correct) rarely exceed 50% for even the best performers. For developers building data extraction pipelines, agents that read invoices, or any system where "correct JSON" means more than syntactically valid JSON, this is required reading. The dataset is on Hugging Face, the paper is on arXiv, and the playground lets you test your own model's structured output capability directly.
Developer Tools
Skills (mattpocock)
Real-world agent skills for engineers — install via npm, not vibes
75%
Panel ship
—
Community
Free
Entry
Skills is a curated library of AI agent prompts and workflows for real software engineering, created by TypeScript educator Matt Pocock. The project trended to 28,000 GitHub stars with its blunt tagline: "Agent skills for real engineers — not vibe coding." It's a deliberate pushback against chaos-first AI coding in favor of structured, methodical engineering. The library organizes into four categories: Planning & Design (to-prd for converting conversations into PRDs, grill-me for stress-testing plans), Development (tdd for test-driven AI assistance, triage-issue for bug investigation), Tooling & Setup (pre-commit hooks, git safety guards), and Writing & Knowledge (documentation utilities, Obsidian integration). Each skill installs with a single npx command — npx skills@latest add mattpocock/skills/tdd — and plugs into Claude agent setups. With 28,000 stars and 2,200 forks after trending on GitHub on April 27, 2026, Skills has clearly struck a nerve. It's as much a cultural statement as a product: AI coding tools should be used deliberately, with tests, with planning, and with guardrails. The TDD and triage-issue skills address real gaps in how current AI coding agents handle existing codebases rather than greenfield projects.
Reviewer scorecard
“This is the benchmark I've been waiting for. 'Valid JSON' is table stakes — the real question is whether field values are correct. This plugs a genuine gap in how we evaluate extraction pipelines.”
“The tdd skill alone is worth the install. Watching a Claude agent plan tests before writing implementation is exactly how I want AI to assist me. Matt's framing of 'real engineering vs. vibe coding' is the right cultural correction for 2026.”
“The 23.7% audio accuracy stat sounds alarming but the test data is text-normalized before scoring, meaning ASR errors are excluded. It's a better benchmark than most but the methodology choices deserve more scrutiny before you rely on it for vendor selection.”
“These are sophisticated markdown prompts, not magic. If you're already a disciplined engineer, the skills add ceremony without much acceleration. The 28K stars partly reflect Matt's Twitter following — evaluate the actual skills before star-chasing.”
“No universal winner across modalities is the real story here. As agentic systems increasingly handle mixed-media inputs, this exposes that model selection needs to be task-specific. Benchmarks like SOB are how the industry gets smarter about that.”
“Community-curated skill libraries installed via package managers will become standard infrastructure — as natural as installing a linting config. Skills is the early prototype of a skills ecosystem that will matter at scale.”
“For anyone automating content workflows that extract structured data from documents, briefs, or meeting recordings, this tells you which model to actually trust for each media type. Genuinely useful before you commit to an architecture.”
“The writing and knowledge skills are underrated. The article-editing and Obsidian integration skills bring structured AI assistance to documentation workflows that most agent tools ignore entirely. Install even if you're not primarily a developer.”
Weekly AI Tool Verdicts
Get the next comparison in your inbox
New AI tools ship daily. We compare them before you waste an afternoon.