CUJBench (Retrieval Baseline): leaderboard
Metric: Root-cause accuracy: single-prediction root-cause accuracy (A@1, %: component and fault type both correct; a run that never submits counts as wrong) on the 25-scenario CUJBench evaluation subset of browser-to-backend failure diagnoses (OpenTelemetry Demo and Tractor Store applications), one run per scenario; no tool loop: BM25-retrieved chunks of the text-serialized evidence are given in a single call, without screenshots; higher is better. Source: arxiv.org. Saturation forecast: Around 2038. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 20 |
| 2 | Llama 4 Scout | 12 |
| 3 | GLM-4.6V | 12 |
| 4 | Qwen 3 VL 235B A22B Instruct | 8 |
| 5 | Gemini 3.1 Pro (Preview) | 4 |
Interactive version: theaggregate.ai/benchmark?slug=cujbench-retrieval-baseline · How It Works · Data refreshed daily, snapshot 2026-10-07.