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...

CodeElo — leaderboard

Metric: Elo Rating. Source: codeelo-bench.github.io. 33 models tracked.

Top models

#ModelScore
1Human Expert3979
2O1 Mini1578
3QwQ 32B-Preview1261
4Median Human1200
5Qwen 2.5 72B Instruct634
6Mistral Large 2 (Nov) Instruct (2411)631
7Qwen 2.5 Coder 32B Instruct575
8Qwen 2.5 32B Instruct513
9Llama 3.1 70B Instruct478
10Qwen 2.5 Coder 14B Instruct424
11Qwen 2.5 14B Instruct414
12Qwen 2.5 Coder 7B Instruct397
13Codestral-22B-v0.1385
14Qwen 2.5 7B Instruct315
15Yi-Coder-9B-Chat296

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