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...

ATRBench — leaderboard

Metric: TSAcc Default (%) (self-reported). Source: benchmarklist.com. 8 models tracked.

Top models

#ModelScore
1DeepSeek V4 Flash23.7
2Claude Opus 4.722.2
3MiniMax-M2.720.4
4Qwen 3.6 Plus20.3
5Gemini 3.1 Pro (Preview)20.1
6DeepSeek V4 Pro20
7Gemini 3 Flash (Preview)15.6
8GPT-5.415

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