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 (Opus 4.6 System Card) — leaderboard

Metric: Pass Rate (%). Source: www-cdn.anthropic.com. 5 models tracked.

Top models

#ModelScore
1Claude Opus 4.6 (Thinking)65.4
2GPT-5.264.7
3Claude Opus 4.5 (Thinking)59.8
4Gemini 3 Pro56.2
5Claude Sonnet 4.551

Interactive version: theaggregate.ai/benchmark?slug=terminal-bench-2-0-opus-4-6-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.