SWE-Recreation - Full Credit Share: leaderboard

SWE-Recreation (arXiv 2611.26311v1) software-recreation benchmark (Full Credit Share) grading coding agents rebuilding unfamiliar web/Android apps from pixels.

Metric: Full-Credit Requirement Share (%). Source: arxiv.org. Saturation forecast: Around November 2028. 5 models tracked. Updated 22 Nov 2026.

Top models

#ModelScoreOverall rank
1Kimi K322.9#62
2DeepSeek V4.1 Flash18.9#69
3GLM-5.3 Flash13.5#137
4GPT-6 Sol13.4#33
5Claude Opus 4.85.2#64

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=swe-recreation-full-credit-share · How It Works · Data refreshed daily, snapshot 2026-11-22.