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...

P3B3 — leaderboard

Metric: LLM pt-PT (↑) (self-reported). Source: benchmarklist.com. 20 models tracked.

Top models

#ModelScore
1Gemini 3 Flash (Preview)99.8
2Gemma 4 31B98
3Gemma 4 E4B94.4
4Qwen 3.5 27B93.3
5Gemma 3 12B92.9
6Ministral 3 14B90.7
7Qwen 3.5 9B86.1
8Llama 3.3 70B Instruct67.8
9Llama 3.1 8B47.7
10Qwen 3 8B32.7

Interactive version: theaggregate.ai/benchmark?slug=p3b3 · 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.