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...

Loong — leaderboard

Metric: Overall Avg Score (%). Source: github.com. 11 models tracked.

Top models

#ModelScore
1Gemini 1.5 Pro55.37
2GPT-4o53.47
3Claude 3.5 Sonnet48.85
4Claude 3 Haiku44.88
5Qwen 2 72B Instruct43.29
6GPT-4o Mini42.95
7GLM-4 9B Chat38.31
8Llama 3.1 8B Instruct36.31

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