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...

TerminalWorld — leaderboard

Metric: Pass Rate (%, 200 verified tasks). Source: terminalworld.ai. 8 models tracked.

Top models

#ModelScore
1Claude Opus 4.762.5
2Kimi K2.657.5
3GLM-5.157
4Gemini 3.1 Pro (Preview)55
5Qwen 3.6 Max Preview54
6GPT-5.553.5
7DeepSeek V4 Pro50
8MiniMax-M2.749

Interactive version: theaggregate.ai/benchmark?slug=terminalworld · 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.