Qwen3.7 Launch - Skillsbench — leaderboard
Metric: Score (%). Source: qwen.ai. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.7 Max | 59.2 |
| 2 | Kimi K2.6 (Thinking) | 56.2 |
| 3 | GLM-5.1 (Thinking) | 53.1 |
| 4 | DeepSeek V4 Pro (Reasoning, Max Effort) | 52.3 |
| 5 | Qwen 3.6 Plus | 45.7 |
Interactive version: theaggregate.ai/benchmark?slug=qwen3-7-launch-skillsbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.