CTBench - Root Cause Identification: leaderboard
Metric: IoU of root-cause label sets (%). Source: arxiv.org. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Codex + GPT-5.5 | 66.83 |
| 2 | Hermes Agent + Qwen3.7-Max | 52.38 |
| 3 | Hermes Agent + DeepSeek-V4-Pro | 40.08 |
| 4 | Claude Code + Qwen3.7-Plus | 38.96 |
| 5 | Hermes Agent + TelecomGPT-R1 | 11.37 |
Interactive version: theaggregate.ai/benchmark?slug=ctbench-root-cause-identification · How It Works · Data refreshed daily, snapshot 2026-09-19.