Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

Qwen3.7 Launch - Kernel Bench L3 - Win Rate — leaderboard

Metric: Problems faster than torch.compile (%). Source: qwen.ai. 6 models tracked.

Top models

#ModelScore
1Claude Opus 4.6 (Thinking)98
2Qwen 3.7 Max96
3Kimi K2.6 (Thinking)80
4GLM-5.1 (Thinking)78
5DeepSeek V4 Pro (Reasoning, Max Effort)54
6Qwen 3.6 Plus48

Interactive version: theaggregate.ai/benchmark?slug=qwen3-7-launch-kernel-bench-l3-win-rate · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.