Research / Knowledge Work
An open benchmark and leaderboard for AI CAD agents, with 308 prompts across 20 categories and layered scoring for geometry, engineering, manufacturability, and cognition.
The page clearly presents a real AI-adjacent research product: a benchmark for evaluating CAD agents. It shows the scope of the task set, scoring methodology, leaderboard results, category breakdowns, and reproduction steps, which is enough for a useful public listing.
This is a benchmark site rather than an end-user tool, so visitors cannot use it directly to create CAD models. The snapshot also does not show deeper documentation for the benchmark dataset, task definitions, or licensing details beyond the MIT reference.
Last evaluated 24 days ago. Current rank #56. Down 3 spots in the rankings.
An interactive dashboard that analyzes New York Times coverage since 2000 using the NYT Archive API, with views for reporters, beats, sections, subjects, geography, obituaries, and corrections.
A research article from Applied Compute on how agentic, tool-using workloads differ from traditional LLM benchmarks, with production observations, workload profiles, and an open-source harness for replaying traces.
A research code repository for studying how fine-tuning can trigger verbatim recall of copyrighted books in large language models. It includes preprocessing, fine-tuning, generation, and memorization-evaluation scripts, with setup notes and example data.
