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...

Terminal-Bench 2.0 (Mythos Preview System Card) — leaderboard

Metric: Mean Reward (%). Source: www-cdn.anthropic.com. 4 models tracked.

Top models

#ModelScore
1Claude Mythos Preview82
2GPT-5.475.1
3Gemini 3.1 Pro (Preview)68.5
4Claude Opus 4.665.4

Interactive version: theaggregate.ai/benchmark?slug=terminal-bench-2-0-mythos-preview-system-card · 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.