Skip to content
The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps Task Explorer
How It Works Guesswork Metrics
The Aggregate
Loading data...

CodeRouterBench (OOD) — leaderboard

Metric: Resolve Rate (%). Source: huggingface.co. 8 models tracked.

Top models

#ModelScore
1GPT-5.464.2
2Claude Opus 4.663.64
3GLM-544.89
4Claude Sonnet 4.643.18
5MiniMax-M2.735.23
6Qwen 3 Max32.95
7Qwen 3.5 Plus27.27
8Kimi K2.519.89

Interactive version: theaggregate.ai/benchmark?slug=coderouterbench-ood · How It Works · Data refreshed daily, snapshot 2026-07-27.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.