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...

CulMind — leaderboard

Metric: S (self-reported). Source: benchmarklist.com. 14 models tracked.

Top models

#ModelScore
1Gemini 3 Flash (Preview)50.7
2Qwen 3 VL 8B Instruct48.7
3Qwen 3 VL 32B Instruct46.6
4GPT-5.545.9
5Gemini 2.5 Flash44.7
6GLM-4.5V43.8
7InternVL3-8B42.8
8InternVL3-14B42.5
9GPT-5.4 Mini39.9
10Qwen 3.5 27B39.7
11Qwen 3.5 9B37.5

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