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...

VIBench — leaderboard

Metric: Direct VIB (self-reported). Source: benchmarklist.com. 10 models tracked.

Top models

#ModelScore
1Gemini 2.5 Flash18.8
2GPT-5.4 Mini7.9
3Granite 4.0 H Small2.9
4Granite 4.0 H 1B2.6
5GPT-5.40.5
6Qwen 3.6 Plus0
7Gemini 2.5 Pro-4.5
8Nova 2 Lite-13.8

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