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...

BehaviorBench — leaderboard

Metric: Game Behav. Sim. (W ↓) (self-reported). Source: benchmarklist.com. 20 models tracked.

Top models

#ModelScore
1GPT-5.431.4
2Gemini 3.1 Flash31.3
3GPT-5.4 Mini29
4GPT-4.127.5
5Claude Opus 4.626
6Claude Sonnet 4.624.6
7Claude Haiku 4.524.5
8Llama 3.3 70B Instruct24.2
9Gemini 3.1 Pro (Preview)21.3
10DeepSeek V3.216.9

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