BackendForge (Base Oracle): leaderboard
Metric: Task success rate (%; base oracle of 7,250 items written before the reference implementation; 56 contract-defined backend services rewritten from open-source applications; from a visible spec and OpenAPI contract the agent builds a Dockerized Python service, scored only through black-box HTTP pytest items; a task counts only when every item passes; one attempt per task in the same mini-SWE-style coding harness). Source: arxiv.org. Saturation forecast: Around December 2026. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 (Max) | 58.93 |
| 2 | GPT-5.5 (xHigh) | 55.36 |
| 3 | Kimi K2.6 | 39.29 |
| 4 | Claude Sonnet 4.6 (Max) | 39.29 |
| 5 | DeepSeek V4 Pro (Max) | 32.14 |
| 6 | GLM-5.1 | 26.79 |
| 7 | DeepSeek V4 Pro (High) | 25 |
| 8 | Gemini 3.5 Flash | 21.43 |
| 9 | DeepSeek V4 Flash (High) | 21.43 |
| 10 | DeepSeek V4 Flash (Max) | 19.64 |
| 11 | Hy3-preview (High) | 12.5 |
| 12 | MiniMax-M2.7 | 5.36 |
Interactive version: theaggregate.ai/benchmark?slug=backendforge-base-oracle · How It Works · Data refreshed daily, snapshot 2026-09-29.