# Consultation Capability Evaluation on ClinicalBench Source: [Consultation Capability Evaluation on ClinicalBench]() Collection index: [llms.txt]() Data updated: 2026-04-13T08:19:49.257Z Evaluation of model performance on assessing consultation capability using the ClinicalBench dataset, focusing on conversational structure, professional jargon, and amiable behavior. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Consultation Capability Evaluation | | Dataset (including any stated split) | ClinicalBench | | Metric | Conversation Arrangement | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 19 of 19 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Conversation Arrangement](): Higher is better; unit: SCALAR. - [Question Types](): Higher is better; unit: SCALAR. - [Verifications](): Higher is better; unit: SCALAR. - [Professional Jargon](): Higher is better; unit: SCALAR. - [Speech](): Higher is better; unit: SCALAR. - [Amiable Behavior](): Higher is better; unit: SCALAR. - [Conversation Turns](): Higher is better; unit: SCALAR. ## Recorded results | Method | Conversation Arrangement | Result date | Report paper | | --- | --- | --- | --- | | MiniMax-M2 | 4.04 | Not recorded | 69dc785a7d0172140ec788be | | Kimi K2 Thinking | 4.02 | Not recorded | 69dc785a7d0172140ec788be | | Aegle | 4.02 | Not recorded | 69dc785a7d0172140ec788be | | HuatuoGPT-o1-7B | 4.01 | Not recorded | 69dc785a7d0172140ec788be | | DeepSeek-V3.2 | 4.01 | Not recorded | 69dc785a7d0172140ec788be | | Qwen3-Max | 4.01 | Not recorded | 69dc785a7d0172140ec788be | | Qwen3-8B-think | 4 | Not recorded | 69dc785a7d0172140ec788be | | Lingshu-32B | 4 | Not recorded | 69dc785a7d0172140ec788be | | DeepSeek-V3.2-Thinking | 4 | Not recorded | 69dc785a7d0172140ec788be | | GLM-4.6 | 4 | Not recorded | 69dc785a7d0172140ec788be | | GPT-4o | 4 | Not recorded | 69dc785a7d0172140ec788be | | Doubao-Seed-1.6 | 4 | Not recorded | 69dc785a7d0172140ec788be | | ERNIE-5.0-Preview | 4 | Not recorded | 69dc785a7d0172140ec788be | | CoT | 4 | Not recorded | 69dc785a7d0172140ec788be | | ToT | 4 | Not recorded | 69dc785a7d0172140ec788be | | MDAgents | 4 | Not recorded | 69dc785a7d0172140ec788be | | MedAgents | 4 | Not recorded | 69dc785a7d0172140ec788be | | Baichuan-M2-32B | 3.99 | Not recorded | 69dc785a7d0172140ec788be | | Gemini 2.5 | 3.88 | Not recorded | 69dc785a7d0172140ec788be | ### MiniMax-M2 Conversation Arrangement: 4.04. Result ID: 69dca5eb47f34ce924c38462. [Reporting paper]() Recorded evaluation configuration: {"Open-source":"true"}. This record does not assert independent reproduction. ### Kimi K2 Thinking Conversation Arrangement: 4.02. Result ID: 69dca5eb47f34ce924c38461. [Reporting paper]() Recorded evaluation configuration: {"Open-source":"true"}. This record does not assert independent reproduction. ### Aegle Conversation Arrangement: 4.02. Result ID: 69dca5eb47f34ce924c3846c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### HuatuoGPT-o1-7B Conversation Arrangement: 4.01. Result ID: 69dca5eb47f34ce924c3845a. [Reporting paper]() Recorded evaluation configuration: {"Open-source":"true","Medical-domain":"true"}. This record does not assert independent reproduction. ### DeepSeek-V3.2 Conversation Arrangement: 4.01. Result ID: 69dca5eb47f34ce924c3845e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Open-source":"true"}. This record does not assert independent reproduction. ### Qwen3-Max Conversation Arrangement: 4.01. Result ID: 69dca5eb47f34ce924c38465. [Reporting paper]() Recorded evaluation configuration: {"Proprietary":"true"}. This record does not assert independent reproduction. ### Qwen3-8B-think Conversation Arrangement: 4. Result ID: 69dca5eb47f34ce924c3845b. [Reporting paper]() Recorded evaluation configuration: {"Open-source":"true"}. This record does not assert independent reproduction. ### Lingshu-32B Conversation Arrangement: 4. Result ID: 69dca5eb47f34ce924c3845d. [Reporting paper]() Recorded evaluation configuration: {"Open-source":"true","Medical-domain":"true"}. This record does not assert independent reproduction. ### DeepSeek-V3.2-Thinking Conversation Arrangement: 4. Result ID: 69dca5eb47f34ce924c3845f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Open-source":"true"}. This record does not assert independent reproduction. ### GLM-4.6 Conversation Arrangement: 4. Result ID: 69dca5eb47f34ce924c38460. [Reporting paper]() Recorded evaluation configuration: {"Open-source":"true"}. This record does not assert independent reproduction. ### GPT-4o Conversation Arrangement: 4. Result ID: 69dca5eb47f34ce924c38463. [Reporting paper]() Recorded evaluation configuration: {"Proprietary":"true"}. This record does not assert independent reproduction. ### Doubao-Seed-1.6 Conversation Arrangement: 4. Result ID: 69dca5eb47f34ce924c38466. [Reporting paper]() Recorded evaluation configuration: {"Proprietary":"true"}. This record does not assert independent reproduction. ### ERNIE-5.0-Preview Conversation Arrangement: 4. Result ID: 69dca5eb47f34ce924c38467. [Reporting paper]() Recorded evaluation configuration: {"Proprietary":"true"}. This record does not assert independent reproduction. ### CoT Conversation Arrangement: 4. Result ID: 69dca5eb47f34ce924c38468. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### ToT Conversation Arrangement: 4. Result ID: 69dca5eb47f34ce924c38469. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### MDAgents Conversation Arrangement: 4. Result ID: 69dca5eb47f34ce924c3846a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### MedAgents Conversation Arrangement: 4. Result ID: 69dca5eb47f34ce924c3846b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"DeepSeek-V3.2"}. This record does not assert independent reproduction. ### Baichuan-M2-32B Conversation Arrangement: 3.99. Result ID: 69dca5eb47f34ce924c3845c. [Reporting paper]() Recorded evaluation configuration: {"Open-source":"true","Medical-domain":"true"}. This record does not assert independent reproduction. ### Gemini 2.5 Conversation Arrangement: 3.88. Result ID: 69dca5eb47f34ce924c38464. [Reporting paper]() Recorded evaluation configuration: {"Proprietary":"true"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.