# KlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy

arXiv: https://arxiv.org/abs/2609.38480 · HTML: https://mlsanity.com/paper/2609.38480/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 28 of 28)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering](https://mlsanity.com/paper/2203.14371/) (2022)
- [Towards Conversational Diagnostic AI](https://mlsanity.com/paper/2401.05654/) (2024)
- [An Agentic System for Rare Disease Diagnosis with Traceable Reasoning](https://mlsanity.com/paper/2506.20430/) (2025)
- [Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulator](https://mlsanity.com/paper/2403.08495/) (2024)
- [HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats](https://mlsanity.com/paper/2604.27470/) (2026)
- [MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis](https://mlsanity.com/paper/2502.19175/) (2025)
- [PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments](https://mlsanity.com/paper/2605.02240/) (2026)
- [MedMT-Bench: Can LLMs Memorize and Understand Long Multi-Turn Conversations in Medical Scenarios?](https://mlsanity.com/paper/2603.23519/) (2026)
- [LongMedBench: Benchmarking Medical Agents for Long-Horizon Clinical Decision-Making](https://mlsanity.com/paper/2607.09322/) (2026)
- [MedConsultBench: A Full-Cycle, Fine-Grained, Process-Aware Benchmark for Medical Consultation Agents](https://mlsanity.com/paper/2601.12661/) (2026)
- [MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents](https://mlsanity.com/paper/2606.03203/) (2026)
- [RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skills](https://mlsanity.com/paper/2606.18203/) (2026)
- [MedLoCoMo: A Long-Context Multi-Session Medical Dialogue Benchmark for Large Language Models](https://mlsanity.com/paper/2607.22566/) (2026)
- [Synthesis and Evaluation of Long-term History-aware Medical Dialogue](https://mlsanity.com/paper/2605.19766/) (2026)
- [MedConceal: A Benchmark for Clinical Hidden-Concern Reasoning Under Partial Observability](https://mlsanity.com/paper/2604.08788/) (2026)
- [ObGynLongBench: Revealing the Evidence-to-EHR Gap in Longitudinal EHR Decision-Making](https://mlsanity.com/paper/2609.07601/) (2026)

## Abstract (arXiv)

Most clinical benchmarks evaluate language models (LMs) on diagnosis using complete case descriptions. In clinical practice, however, patients present information in different ways, and clinicians must obtain relevant history and determine which examinations are needed before reaching a diagnosis. Diagnostic accuracy alone therefore cannot establish whether an agent gathered essential information or conducted an appropriate clinical assessment. Furthermore, existing benchmarks lack professional clinicians' verification. To address this gap, we introduce KlinikeBench, a benchmark of 333 clinician-authored tasks, each providing an isolated sandbox environment with a virtual patient, clinical tools, and task-specific success criteria. More than 35 clinicians contributed to case authoring and benchmark evaluation. In an empirical study, clinicians gave simulated dialogues higher mean quality ratings than reference conversations, which is adapted from real conversation. In each task, an LM has a fixed budget of turns to communicate with the patient, ask about relevant history, request examinations, follow action constraints, and record a final diagnosis. We score these steps separately as well as together. Across 31 models and seven model families, the best-performing models (e.g., GPT-6-astra and Claude Opus 5) succeed on less than 30% of tasks, even though their diagnosis accuracy reaches 90.7%. Some models benefit from talking with the patient; others diagnose well from a complete chart but perform much worse in conversation. Overall, KlinikeBench provides a testbed for evaluating the full clinical encounter and reveals a substantial gap between diagnostic accuracy and performance in interactive clinical assessment. All the code and data is available on https://zehui127.github.io/klinikebench/