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...

PlanningBench — leaderboard

Metric: All-pass (%) (self-reported). Source: benchmarklist.com. 16 models tracked.

Top models

#ModelScore
1GPT-5.4 (xHigh)63.17
2Gemini 3.1 Pro (Preview)53.25
3DeepSeek V3.237.13
4Hy3-preview36.17
5Qwen 3.5 Plus (Thinking)34.03
6Gemini 2.5 Pro31.7
7DeepSeek V3.2 Exp29.27
8Seed 1.822.4
9Qwen 3 32B0.27
10Qwen 3 8B0
11Qwen 3 14B0

Interactive version: theaggregate.ai/benchmark?slug=planningbench · 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.