CodeRouterBench - LLM Router (3-Shot): leaderboard
Model routing for coding tasks from Agent-as-a-Router (Zhou et al., 2026): the model reads each of the 2,919 in-distribution CodeRouterBench coding tasks and picks which of eight candidate LLMs should solve it, after three examples from the same coding dimension that show the best model and all eight scores. Score is the average recorded task score in percent of the chosen models, where a missing result counts 0; higher is better.
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; three same-dimension probing examples with oracle labels and all eight scores). Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5 | 46.03 | #256 |
| 2 | Qwen 3 Max | 45.8 | #401 |
| 3 | GPT-5.4 | 45.66 | #121 |
| 4 | Claude Sonnet 4.6 | 45.53 | #158 |
| 5 | Qwen 3.5 Plus | 45.39 | #227 |
| 6 | MiniMax-M2.7 | 45.29 | #519 |
| 7 | Kimi K2.5 | 45.1 | #252 |
| 8 | Claude Opus 4.6 | 41.17 | #100 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=coderouterbench-llm-router-3-shot · How It Works · Data refreshed daily, snapshot 2026-11-12.