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...

Causal Sensitivity Score (CSS) — leaderboard

Metric: CSS (self-reported). Source: benchmarklist.com. 6 models tracked.

Top models

#ModelScore
1Grok 4.2047.3
2GPT-5.4 Mini43.9
3Claude Opus 4.743.2
4GPT-542.7
5Claude Sonnet 4.639.4
6GPT-5.430.9

Interactive version: theaggregate.ai/benchmark?slug=causal-sensitivity-score-css · 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.