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...

LABBench2 - Patent Questions (Anthropic) — leaderboard

Metric: Score (%). Source: www-cdn.anthropic.com. 3 models tracked.

Top models

#ModelScore
1Claude Opus 4.868.8
2Claude Mythos Preview64.3
3Claude Opus 4.748.3

Interactive version: theaggregate.ai/benchmark?slug=labbench2-patent-questions-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.