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...

LithoBench — leaderboard

Metric: MCQ$_{\mathrm{all}}$ (self-reported). Source: benchmarklist.com. 13 models tracked.

Top models

#ModelScore
1Qwen 3.5 9B98.25
2GLM-4.6V94.5
3GPT-5.493
4Qwen 3.5 397B A17B92.77
5Claude Sonnet 4.679.15
6Qwen 3.5 27B77.2
7Grok 476.05

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