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...

SWE-bench Pro (Anthropic Scaffold) — leaderboard

Metric: Pass@1 (%). Source: www-cdn.anthropic.com. 6 models tracked.

Top models

#ModelScore
1Claude Mythos 580.3
2Claude Fable 580
3Claude Mythos Preview77.8
4Claude Opus 4.869.2
5GPT-5.558.6
6Gemini 3.1 Pro (Preview)54.2

Interactive version: theaggregate.ai/benchmark?slug=swe-bench-pro-anthropic-scaffold · 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.