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...

FrontierCode Diamond — leaderboard

Metric: Score (%). Source: cognition.ai. 12 models tracked.

Top models

#ModelScore
1Claude Opus 4.813.4
2GPT-5.56.3
3Claude Opus 4.75.2
4Gemini 3.1 Pro (Preview)4.7
5GPT-5.4 Mini4.6
6Kimi K2.63.8
7Claude Sonnet 4.63.5
8MiniMax-M2.72.4
9MiniMax-M2.51.1
10Kimi K2.51
11Gemini 3.1 Flash Lite0.7

Interactive version: theaggregate.ai/benchmark?slug=frontiercode-diamond · 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.