Qwen3.7 Launch - SWE-Pro — leaderboard
Metric: Resolved (%). Source: qwen.ai. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.7 Max | 60.6 |
| 2 | Kimi K2.6 (Thinking) | 59.5 |
| 3 | DeepSeek V4 Pro (Reasoning, Max Effort) | 59 |
| 4 | GLM-5.1 (Thinking) | 58.8 |
| 5 | Claude Opus 4.6 (Thinking) | 57.3 |
| 6 | Qwen 3.6 Plus | 56.6 |
Interactive version: theaggregate.ai/benchmark?slug=qwen3-7-launch-swe-pro · How the rankings work · Data refreshed daily, snapshot 2026-07-22.