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...

PECC - Advent of Code (LeetCode-style) — leaderboard

Metric: Solve rate (%). Source: huggingface.co. 11 models tracked.

Top models

#ModelScore
1WizardCoder-Python-34B-V1.022.5
2Mixtral 8x7B Instruct (v0.1)13.01
3Phi-3 Mini 128K Instruct13
4WizardLM-2-7B6.89
5Llama 3 8B Instruct6.38
6Mistral 7B Instruct (v0.1)3

Interactive version: theaggregate.ai/benchmark?slug=pecc-advent-of-code-leetcode-style · 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.