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...

ROK-FORTRESS — leaderboard

Metric: Δ_ling (pp) (self-reported). Source: benchmarklist.com. 14 models tracked.

Top models

#ModelScore
1Mistral Large 328.4
2Llama 4 Maverick17.4
3DeepSeek V316.3
4Claude Sonnet 4.510.7
5Claude Opus 4.58.3
6GPT-5.24.3
7O4 Mini3.9
8Qwen 3 235B A22B-3

Interactive version: theaggregate.ai/benchmark?slug=rok-fortress · 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.