FDE-Bench - Orchestration: leaderboard
Metric: Resolved rate (%; the 48 orchestration-axis tasks (Compose stacks and Kubernetes manifests); 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 February 2027. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.6 Flash | 72.9 |
| 2 | DeepSeek V4 Pro | 68.8 |
| 3 | Claude Sonnet 5 (High) | 68.8 |
| 4 | GPT-5.6 Terra | 64.6 |
| 5 | Gemini 3.5 Flash Lite | 62.5 |
| 6 | GPT-5.6 Luna | 60.4 |
| 7 | DeepSeek V4 Flash | 58.3 |
Interactive version: theaggregate.ai/benchmark?slug=fde-bench-orchestration · How It Works · Data refreshed daily, snapshot 2026-09-26.