Qwen3.7 Launch - Kernel Bench L3 - Median Speedup — leaderboard
Metric: Median speedup (x). Source: qwen.ai. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 (Thinking) | 2.63 |
| 2 | GLM-5.1 (Thinking) | 2 |
| 3 | Qwen 3.7 Max | 1.98 |
| 4 | Kimi K2.6 (Thinking) | 1.41 |
| 5 | DeepSeek V4 Pro (Reasoning, Max Effort) | 1.07 |
| 6 | Qwen 3.6 Plus | 1.03 |
Interactive version: theaggregate.ai/benchmark?slug=qwen3-7-launch-kernel-bench-l3-median-speedup · How the rankings work · Data refreshed daily, snapshot 2026-07-22.