CTBench - Root Cause Identification: leaderboard

Metric: IoU of root-cause label sets (%). Source: arxiv.org. 5 models tracked.

Top models

#ModelScore
1Codex + GPT-5.566.83
2Hermes Agent + Qwen3.7-Max52.38
3Hermes Agent + DeepSeek-V4-Pro40.08
4Claude Code + Qwen3.7-Plus38.96
5Hermes Agent + TelecomGPT-R111.37

Interactive version: theaggregate.ai/benchmark?slug=ctbench-root-cause-identification · How It Works · Data refreshed daily, snapshot 2026-09-19.