Skip to content
The Aggregate

Unified LLM rankings, daily

Models Task Explorer Subscriptions What's New Trends Benchmarks Builder Guesswork
How It Works Daily brief
The Aggregate
Loading data...

HAE-GEO - Clean Answer Quality: leaderboard

Metric: Rubric Score (0-2). Source: arxiv.org. 10 models tracked.

Top models

#ModelScore
1GPT-5.6 Sol1.53
2Qwen 3.5 397B A17B1.53
3Qwen 3.6 35B A3B1.53
4MiniMax-M31.45
5Kimi K31.43
6Qwen 3.8 27B1.43
7GLM-5.21.42
8Claude Opus 4.81.35
9DeepSeek V4 Flash1.34
10GLM-4.7 Flash1.18

Interactive version: theaggregate.ai/benchmark?slug=hae-geo-clean-answer-quality · How It Works · Data refreshed daily, snapshot 2026-09-21.

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

Your Aggregate

Sign in to keep your work

Save custom rankings and get 50 free task analyses each day.

Continue with Google Continue with GitHub

No password to remember. Your public profile identifies saved work.

Your Aggregate

Account

  • Saved custom aggregate views
  • 50 free task analyses per day
Sign out