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...

Beyond Pass Rate — leaderboard

Metric: Correctness (%). Source: arxiv.org. 9 models tracked.

Top models

#ModelScore
1Yi-Coder-9B23.6
2Qwen 2.5 14B22.2
3Gemma 2 27B18.9
4Phi-410.3
5Llama 3.1 8B8.1

Interactive version: theaggregate.ai/benchmark?slug=beyond-pass-rate · 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.