SWE-Cycle - Code Implementation Solve Rate: leaderboard

SWE-Cycle Code Implementation Solve Rate is the percent of 489 filtered SWE-bench issues where a code agent completes the isolated task to implement the issue in a preconfigured codebase with full marks on both static review and execution (SWE-Cycle, 2026). Higher is better.

Metric: Solve rate (%): share of issues with a perfect score (full marks on both static and dynamic checks by SWE-Judge (Claude Opus 4.5 agent) static code review and dynamic execution, each scored 0, 1 or 2), on the 489 SWE-Cycle issues (225 SWE-bench Verified, 203 SWE-bench Pro, 61 SWE-bench Multilingual, filtered for contamination, lifecycle complexity and reliable tests); isolated Impl: implement the issue in a preconfigured codebase (90 minutes); agents run in the OpenCode harness in isolated Docker containers; higher is better. Source: arxiv.org. Saturation forecast: Around May 2027. 6 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Sonnet 4.640.08#173
2GPT-5.439.67#135
3GLM-5.137.83#198
4Kimi K2.534.46#266
5MiniMax-M2.730.88#539
6SWE-Cycle Qwen-3.5 (checkpoint unspecified)28.83

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=swe-cycle-code-implementation-solve-rate · How It Works · Data refreshed daily, snapshot 2026-11-21.