Articles

analysis14 min

We Benchmarked 7 OCR Models So You Don't Have To

Results from our own olmOCR-bench runs across OCR-specific models, general-purpose VLMs, and Tesseract. The main lesson: evaluation methodology changes scores more than most leaderboard readers realize.

Claude Code is the New Cursor (and the Cycle Never Ends)

Claude Code is the New Cursor (and the Cycle Never Ends)

12 min

When to Build Your Own AI Agent (and When Claude Code Is Enough)

17 min

Which Document AI Benchmarks Actually Matter?

13 min