FDE-Bench - Greenfield: leaderboard

Metric: Resolved rate (%; the 66 greenfield tasks, authored from application source and specification alone; one episode per task, same four-tool scaffold (bash, write_file, read_file, submit), task-specific step, time and token caps; submitted artifacts are rebuilt and redeployed in a pristine sandbox and graded by four gated programmatic check layers (build, readiness, behavior, spec conformance); resolved only if all four pass). Source: arxiv.org. Saturation forecast: Around January 2027. 7 models tracked.

Top models

#ModelScore
1Gemini 3.6 Flash62.1
2GPT-5.6 Terra59.1
3Claude Sonnet 5 (High)57.6
4GPT-5.6 Luna51.5
5DeepSeek V4 Pro50
6DeepSeek V4 Flash42.4
7Gemini 3.5 Flash Lite36.4

Interactive version: theaggregate.ai/benchmark?slug=fde-bench-greenfield · How It Works · Data refreshed daily, snapshot 2026-09-26.