LoopsBench - Claude Code Loop - Resolve Rate: leaderboard
Metric: Resolve rate (%; with outer-loop continuation). Source: arxiv.org. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 20.54 |
| 2 | DeepSeek V4 Pro | 18.75 |
| 3 | GLM-5.1 | 18.75 |
| 4 | Gemini 3.1 Pro (Preview) | 14.29 |
| 5 | Kimi K2.6 | 6.25 |
| 6 | Grok 4.1 Fast (Reasoning) | 4.46 |
Interactive version: theaggregate.ai/benchmark?slug=loopsbench-claude-code-loop-resolve-rate · How It Works · Data refreshed daily, snapshot 2026-09-19.