BenchCAD: Benchmarking Programmatic CAD for Industry
Discover BenchCAD, the industry-standard benchmark for evaluating programmatic CAD models using visual and textual inputs in industrial design.
Generalized Turing Test: New Standard for AI Intelligence
Discover the Generalized Turing Test, a novel framework to compare AI intelligence beyond traditional benchmarks using indistinguishability.
Evaluating AI Pentesting Agents for Real-World Cybersecurity
Discover a new protocol to evaluate AI pentesting agents in complex real-world scenarios, improving vulnerability detection and cybersecurity defense.
Nonlinear Effects of Misleading Info in Long-Context AI
Explore how small amounts of misleading info sharply reduce AI performance in long-context reasoning and why precise retrieval matters.
MaD Physics: AI Measurement Strategies Under Constraints
Discover how MaD Physics benchmark evaluates AI agents' ability to optimize measurements and infer physical laws under resource constraints.