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...

LLM Stats (VITA-Bench) — leaderboard

Metric: Score (%). Source: llm-stats.com. 10 models tracked.

Top models

#ModelScore
1Qwen 3.5 397B A17B49.7
2Qwen 3.7 Max47.9
3Qwen 3.7 Plus45.6
4Qwen 3.6 Plus44.3
5Qwen 3.5 27B41.9
6Qwen 3.6 35B A3B35.6
7Qwen 3.5 122B A10B33.6
8Qwen 3.5 35B A3B31.9
9Qwen 3.5 9B29.8
10Qwen 3.5 4B22

Interactive version: theaggregate.ai/benchmark?slug=llm-stats-vita-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.