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...

Forge — leaderboard

Metric: Overall SR (self-reported). Source: benchmarklist.com. 21 models tracked.

Top models

#ModelScore
1O391.5
2Qwen 3 30B A3B76.8
3Qwen 3 32B70.7
4GPT-4o (2024-08-06)62.1
5Qwen 3 8B57.5
6Qwen 2.5 72B Instruct43.4
7Qwen 2.5 32B41.2
8Qwen 2.5 14B36.2
9Qwen 2.5 7B29.6
10Llama 3.1 8B15.1
11Qwen 2.5 3B13.8

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