Qwen3.7 Launch - SWE-Multilingual — leaderboard
Metric: Resolved (%). Source: qwen.ai. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.7 Max | 78.3 |
| 2 | Claude Opus 4.6 (Thinking) | 77.5 |
| 3 | Kimi K2.6 (Thinking) | 76.7 |
| 4 | DeepSeek V4 Pro (Reasoning, Max Effort) | 76.2 |
| 5 | Qwen 3.6 Plus | 73.8 |
Interactive version: theaggregate.ai/benchmark?slug=qwen3-7-launch-swe-multilingual · How the rankings work · Data refreshed daily, snapshot 2026-07-22.