CodeRouterBench - LLM Router (Online Agent): leaderboard

Metric: Average task score (%) of the backend the model routes each task to, over the 2,919 in-distribution CodeRouterBench coding tasks (execution-graded or proxy scores of eight candidate LLMs, a missing result counting 0); the router picks one of the eight by name; the zero-shot router with a cosine-kNN memory warmed up on 200 validation tasks and updated online as the test stream proceeds, seed 42). Source: arxiv.org. Saturation forecast: Around 2029. 7 models tracked.

Top models

#ModelScore
1MiniMax-M2.745.27
2GLM-545.21
3Qwen 3 Max44.92
4Qwen 3.5 Plus43.98
5Claude Sonnet 4.643.65
6Kimi K2.542.7
7GPT-5.440.95

Interactive version: theaggregate.ai/benchmark?slug=coderouterbench-llm-router-online-agent · How It Works · Data refreshed daily, snapshot 2026-09-26.