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...

KernelBench Hub - Mega — leaderboard

Metric: Best Speedup vs Reference (x). Source: kernelbench.com. 12 models tracked.

Top models

#ModelScore
1Claude Fable 524.61
2Claude Opus 4.819.35
3Kimi K318.09
4GLM-5.211.14
5MiniMax-M34.15
6Claude Sonnet 54.03
7GPT-5.6 Sol2.64
8Kimi K2.7 Code2.59
9DeepSeek V4 Pro2.11
10Grok 4.50.82

Interactive version: theaggregate.ai/benchmark?slug=kernelbench-hub-mega · 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.