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...

OSQ-Bench — leaderboard

Metric: Average. Source: huggingface.co. 7 models tracked.

Top models

#ModelScore
1GPT-4o70.15
2GPT-4 Preview (1106)65.93
3Claude 3 Opus62.53
4Mistral Large60.48
5GPT-3.560.32
6Gemini 1.0 Pro54.06
7Llama 3 70B Instruct52.92

Interactive version: theaggregate.ai/benchmark?slug=osq-bench · 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.