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...

RBench-V — leaderboard

Metric: Overall Score (%). Source: evalmodels.github.io. 28 models tracked.

Top models

#ModelScore
1GPT-5 Mini27.9
2O325.8
3O4 Mini20.9
4Gemini 2.5 Pro (Preview 05-06)20.2
5O116.2
6GPT-4.113.6
7GPT-4.512.6
8Claude 3.7 Sonnet11.5
9InternVL3-38B10
10Llama 4 Scout9.5
11MiniCPM-V-2.69.1
12InternVL3-8B8.2
13InternVL3-14B8
14Qwen2.5-Omni-7B7.7

Interactive version: theaggregate.ai/benchmark?slug=rbench-v · 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.