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...

Prosa — leaderboard

Metric: Score (self-reported). Source: benchmarklist.com. 16 models tracked.

Top models

#ModelScore
1GPT-5.288.6
2GPT-5 Mini84.8
3Qwen 3 235B A22B80.1
4Gemini 3 Flash (Preview)78.8
5Gemini 2.5 Flash76.3
6GPT-4.174.8
7Qwen 3 30B A3B73.9
8GPT-4.1 Mini67.7
9GPT-4o55
10GPT-4o Mini54.5
11Qwen 2.5 14B46.4
12Qwen 2.5 7B43.3

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