Orca-Bench: How Ready Are Language Model Agents for Oncall?

A new benchmark, ORCA-bench, shows that frontier language model agents achieve only 25.3% root cause analysis accuracy on Medium-difficulty oncall tasks and 10.0% on Hard tasks, with the best performance coming from Claude Fable 5, according to a paper submitted to arXiv on July 30, 2026. The benchmark, which pairs a live OpenTelemetry-instrumented microservice system with 1,079 RCA tasks, reveals that the weakest model hallucinates an implausible root cause in 40% of incident reports, and removing source-code access degrades every metric, indicating a significant gap before agents can be trusted with production reliability.

Computer Science Computation and Language Submitted on 30 Jul 2026 Title:ORCA-bench: How Ready Are Language Model Agents for Oncall? View PDF /pdf/2607.28545 HTML experimental https://arxiv.org/html/2607.28545v1 Abstract:Large language models can write, patch, and search code, but oncall root cause analysis RCA demands something different: reasoning over noisy metrics, logs, traces, and source code, starting from ambiguous user-facing reports, often hours after the incident began. We introduce ORCA-bench, a benchmark that puts general-purpose coding agents in a production-fidelity oncall setting. ORCA-bench pairs a live OpenTelemetry-instrumented microservice system--exposing six days of metrics, logs, and traces through real telemetry interfaces Prometheus, Jaeger, and OpenSearch via Grafana and full source-code access--with 1,079 RCA tasks that systematically vary report specificity, time-to-detection, and co-occurring fault scenarios. Ground-truth symptoms are curated and signed off by expert SREs, and our LLM-as-judge is independently re-scored by humans Cohen's $\kappa w=0.90$ . Across five frontier agents, the best RCA Accuracy is 25.3% on Medium-difficulty tasks the realistic-input setting and 10.0% on Hard--a gap that remains even with Claude Fable 5. The weakest model hallucinates an implausible root cause in 40% of incident reports, and removing source-code access degrades every metric. Crucially, these are performances on a curated 50 GB / six-day testbed with tasks investigated in isolation on a system whose code and instrumentation are public. Since real production systems are order of magnitudes larger, more dynamic, and more idiosyncratic, the gap we report is a lower bound on the engineering investment required before frontier coding agents can be safely entrusted with production reliability. We release the public set at this https URL . Current browse context: cs.CL References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .