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...

ProteinGym Hard (Anthropic) — leaderboard

Metric: Rank Correlation (%). Source: www-cdn.anthropic.com. 4 models tracked.

Top models

#ModelScore
1Claude Mythos Preview43.1
2Claude Opus 4.839.6
3Claude Opus 4.737.7
4Claude Sonnet 4.635.4

Interactive version: theaggregate.ai/benchmark?slug=proteingym-hard-anthropic · 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.