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...

CLEAR — leaderboard

Metric: Version (self-reported). Source: benchmarklist.com. 15 models tracked.

Top models

#ModelScore
1Llama 3.2 1B3.2
2Llama 3.1 8B3.1
3Llama 3.1 70B3.1
4Gemma 3 27B3
5Qwen 3 8B3
6Gemma 3 12B3
7Gemma 3 4B3
8Qwen 3 14B3
9Qwen 3 32B3
10Qwen 3 4B3
11Gemma 3 1B3
12Qwen 2.5 72B Instruct2.5
13Qwen 2.5 7B2.5
14Qwen 2.5 3B2.5
15Qwen 2.5 1.5B2.5

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