Research

• Sep 2026 Environments must evolve with models Kennet
• Jul 2026 EnterpriseSWE Benchmark
• May 2026 COBOLBench: Measuring Frontier Agents on Enterprise COBOL Leaderboards
• May 2026 Introducing LegacySWE Essay
• Mar 2026 LH-Bench: Skill-Grounded Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks Paper
• Feb 2026 VideoBench: Evaluating Coding Agents on Source-Grounded Video Generation Leaderboards
• Feb 2026 FigmaBench: Throwing Frontier Models into Real-World Figma Leaderboards
• Dec 2025 Understanding Virality with Vision-Language Models Essay
• Oct 2025 Metaphi SimHub Essay
• Sep 2025 From Static Benchmarks to Dynamic Worlds Essay