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...

ParallelKernelBench Pass@3 — leaderboard

Metric: Pass@3 (% of problems). Source: www.together.ai. 6 models tracked.

Top models

#ModelScore
1GPT-5.541.38
2Claude Opus 4.735.63
3Gemini 3 Pro34.48
4GLM-5.210.34
5GLM-5.18.05
6DeepSeek V4 Pro3.45

Interactive version: theaggregate.ai/benchmark?slug=parallelkernelbench-pass-3 · 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.