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...

Cookie-Bench — leaderboard

Metric: React Overall (self-reported). Source: benchmarklist.com. 13 models tracked.

Top models

#ModelScore
1Claude Opus 4.783.3
2Claude Opus 4.680
3GPT-5.477.8
4MiMo-V2-Pro76.3
5GLM-5.176.2
6Qwen 3.6 Plus75.2
7Qwen 3.6 27B67.2
8Gemini 3.1 Pro (Preview)64.9
9Gemini 3 Flash (Preview)63.3
10Qwen 3.6 35B A3B61.3

Interactive version: theaggregate.ai/benchmark?slug=cookie-bench · 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.