R2ABench (MetaGPT) - GED Accuracy: leaderboard

Requirements-to-architecture generation on R2ABench (2026): from a structured requirements specification of 68 educational and GitHub projects, the model inside an adapted MetaGPT analyst, architect, reviewer and refiner pipeline writes a PlantUML architecture view, compared with a human-validated reference. Normalized graph-edit-distance accuracy between generated and reference graphs, over the views that parse, from 0 to 100; higher is better.

Metric: Normalized graph-edit-distance accuracy (0-100) between the generated and reference architecture graphs (L1), over the 68 R2ABench projects (17 educational and 51 GitHub repositories), generating a PlantUML architecture view from the structured requirements specification with MetaGPT adapted as an analyst, architect, reviewer and refiner agent pipeline under default settings and greedy decoding; scored only over the outputs that render and parse (the L0 gate), failed outputs excluded; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 4 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1MetaGPT + DeepSeek V3.250.27
2MetaGPT + Qwen3-Coder 480B-A35B49.12
3MetaGPT + Claude Sonnet 4.648.26
4MetaGPT + GPT-546.38

Interactive version: theaggregate.ai/benchmark?slug=r2abench-metagpt-ged-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-21.