# Documentation quality evaluation on ClinicalBench 1.0 (test) Source: [Documentation quality evaluation on ClinicalBench 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-04-13T08:19:49.192Z Evaluation of model performance on assessing documentation quality using the test split of the ClinicalBench 1.0 dataset, measured by metrics such as IDEA, SOAP, READ, and chrF++. 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 | Documentation quality evaluation | | Dataset (including any stated split) | ClinicalBench 1.0 (test) | | Metric | IDEA Score | | Unit | PERCENT | | 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 - [IDEA Score](): Higher is better; unit: PERCENT. - [SOAP Score](): Higher is better; unit: PERCENT. - [READ Score](): Higher is better; unit: PERCENT. - [chrF++ Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | IDEA Score | Result date | Report paper | | --- | --- | --- | --- | | Aegle | 72.78 | Not recorded | 69dc785a7d0172140ec788be | | MDAgents | 68.41 | Not recorded | 69dc785a7d0172140ec788be | | ToT | 66.53 | Not recorded | 69dc785a7d0172140ec788be | | CoT | 64.72 | Not recorded | 69dc785a7d0172140ec788be | | Qwen3-Max | 61.75 | Not recorded | 69dc785a7d0172140ec788be | | MedAgents | 59.85 | Not recorded | 69dc785a7d0172140ec788be | | MiniMax-M2 | 57.78 | Not recorded | 69dc785a7d0172140ec788be | | Kimi K2 Thinking | 54.05 | Not recorded | 69dc785a7d0172140ec788be | | Doubao-Seed-1.6 | 51.51 | Not recorded | 69dc785a7d0172140ec788be | | DeepSeek-V3.2 | 50.51 | Not recorded | 69dc785a7d0172140ec788be | | Lingshu-32B | 50.5 | Not recorded | 69dc785a7d0172140ec788be | | Gemini 2.5 | 48.35 | Not recorded | 69dc785a7d0172140ec788be | | ERNIE-5.0-Preview | 47.09 | Not recorded | 69dc785a7d0172140ec788be | | GLM-4.6 | 47.02 | Not recorded | 69dc785a7d0172140ec788be | | DeepSeek-V3.2-Thinking | 46.73 | Not recorded | 69dc785a7d0172140ec788be | | HuatuoGPT-o1-7B | 46.54 | Not recorded | 69dc785a7d0172140ec788be | | Qwen3-8B-think | 43.18 | Not recorded | 69dc785a7d0172140ec788be | | GPT-4o | 41.05 | Not recorded | 69dc785a7d0172140ec788be | | Baichuan-M2-32B | 38.02 | Not recorded | 69dc785a7d0172140ec788be | ### Aegle IDEA Score: 72.78. Result ID: 69dca5eb47f34ce924c38446. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Ours"}. This record does not assert independent reproduction. ### MDAgents IDEA Score: 68.41. Result ID: 69dca5eb47f34ce924c38444. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Category":"Medical multi-agent system"}. This record does not assert independent reproduction. ### ToT IDEA Score: 66.53. Result ID: 69dca5eb47f34ce924c38443. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Category":"Reasoning-strategy baseline"}. This record does not assert independent reproduction. ### CoT IDEA Score: 64.72. Result ID: 69dca5eb47f34ce924c38442. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Reasoning-strategy baseline"}. This record does not assert independent reproduction. ### Qwen3-Max IDEA Score: 61.75. Result ID: 69dca5eb47f34ce924c3843f. [Reporting paper]() Recorded evaluation configuration: {"Proprietary":"true"}. This record does not assert independent reproduction. ### MedAgents IDEA Score: 59.85. Result ID: 69dca5eb47f34ce924c38445. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Category":"Medical multi-agent system"}. This record does not assert independent reproduction. ### MiniMax-M2 IDEA Score: 57.78. Result ID: 69dca5eb47f34ce924c3843c. [Reporting paper]() Recorded evaluation configuration: {"Open-source":"true"}. This record does not assert independent reproduction. ### Kimi K2 Thinking IDEA Score: 54.05. Result ID: 69dca5eb47f34ce924c3843b. [Reporting paper]() Recorded evaluation configuration: {"Open-source":"true"}. This record does not assert independent reproduction. ### Doubao-Seed-1.6 IDEA Score: 51.51. Result ID: 69dca5eb47f34ce924c38440. [Reporting paper]() Recorded evaluation configuration: {"Proprietary":"true"}. This record does not assert independent reproduction. ### DeepSeek-V3.2 IDEA Score: 50.51. Result ID: 69dca5eb47f34ce924c38438. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Open-source":"true"}. This record does not assert independent reproduction. ### Lingshu-32B IDEA Score: 50.5. Result ID: 69dca5eb47f34ce924c38437. [Reporting paper]() Recorded evaluation configuration: {"Open-source":"true","Medical-domain":"true"}. This record does not assert independent reproduction. ### Gemini 2.5 IDEA Score: 48.35. Result ID: 69dca5eb47f34ce924c3843e. [Reporting paper]() Recorded evaluation configuration: {"Proprietary":"true"}. This record does not assert independent reproduction. ### ERNIE-5.0-Preview IDEA Score: 47.09. Result ID: 69dca5eb47f34ce924c38441. [Reporting paper]() Recorded evaluation configuration: {"Proprietary":"true"}. This record does not assert independent reproduction. ### GLM-4.6 IDEA Score: 47.02. Result ID: 69dca5eb47f34ce924c3843a. [Reporting paper]() Recorded evaluation configuration: {"Open-source":"true"}. This record does not assert independent reproduction. ### DeepSeek-V3.2-Thinking IDEA Score: 46.73. Result ID: 69dca5eb47f34ce924c38439. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Open-source":"true"}. This record does not assert independent reproduction. ### HuatuoGPT-o1-7B IDEA Score: 46.54. Result ID: 69dca5eb47f34ce924c38434. [Reporting paper]() Recorded evaluation configuration: {"Open-source":"true","Medical-domain":"true"}. This record does not assert independent reproduction. ### Qwen3-8B-think IDEA Score: 43.18. Result ID: 69dca5eb47f34ce924c38435. [Reporting paper]() Recorded evaluation configuration: {"Open-source":"true"}. This record does not assert independent reproduction. ### GPT-4o IDEA Score: 41.05. Result ID: 69dca5eb47f34ce924c3843d. [Reporting paper]() Recorded evaluation configuration: {"Proprietary":"true"}. This record does not assert independent reproduction. ### Baichuan-M2-32B IDEA Score: 38.02. Result ID: 69dca5eb47f34ce924c38436. [Reporting paper]() Recorded evaluation configuration: {"Open-source":"true","Medical-domain":"true"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.