CUJBench (Full Agent): leaderboard

CUJBench (2026) tests LLM agents on diagnosing the root cause of injected failures in web applications from snapshots of browser evidence and backend observability. This board is root-cause accuracy in percent when the agent can query every browser and backend evidence tool within 15 turns; higher is better.

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; ReAct tool loop capped at 15 turns over all 12 evidence tools (visual, browser and backend); higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 3 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Sonnet 4.644#173
2GLM-4.6V23.8#710
3Gemini 3.1 Pro (Preview)12#99

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=cujbench-full-agent · How It Works · Data refreshed daily, snapshot 2026-11-21.