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...

DVMap — leaderboard

Metric: Accuracy (self-reported). Source: benchmarklist.com. 9 models tracked.

Top models

#ModelScore
1GPT-4o48.5
2Qwen 3 Next 80B A3B47.6
3Llama 3.3 70B Instruct46.4
4GPT-4o Mini46.3
5Qwen 3 14B46.2
6Gemini 2.5 Flash Lite45.3
7DeepSeek V3.2 Exp45.1
8Claude 3.7 Sonnet26.9

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