# Depression Severity Estimation on MMDA (test) Source: [Depression Severity Estimation on MMDA (test)]() Collection index: [llms.txt]() Data updated: 2026-03-10T09:12:53.051Z Evaluation of models for estimating depression severity using the test split of the MMDA dataset, reporting precision, recall, and F1 scores for each severity level (Normal, Mild, Moderate, Severe), along with overall Accuracy and Weighted F1. 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 | Depression Severity Estimation | | Dataset (including any stated split) | MMDA (test) | | Metric | Precision (Normal) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 - [Precision (Normal)](): Higher is better; unit: PERCENT. - [Recall (Normal)](): Higher is better; unit: PERCENT. - [F1 Score (Normal)](): Higher is better; unit: PERCENT. - [Precision (Mild)](): Higher is better; unit: PERCENT. - [Recall (Mild)](): Higher is better; unit: PERCENT. - [F1 Score (Mild)](): Higher is better; unit: PERCENT. - [Precision (Moderate)](): Higher is better; unit: PERCENT. - [Recall (Moderate)](): Higher is better; unit: PERCENT. - [F1 Score (Moderate)](): Higher is better; unit: PERCENT. - [Precision (Severe)](): Higher is better; unit: PERCENT. - [Recall (Severe)](): Higher is better; unit: PERCENT. - [F1 Score (Severe)](): Higher is better; unit: PERCENT. - [Accuracy](): Higher is better; unit: PERCENT. - [Weighted F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Precision (Normal) | Result date | Report paper | | --- | --- | --- | --- | | GPT-4 | 78.6 | Not recorded | 68fa74eb1e209131cea64bbf | | ChineseMentalBert | 66.7 | Not recorded | 68fa74eb1e209131cea64bbf | | InterMind | 66.7 | Not recorded | 68fa74eb1e209131cea64bbf | | InterMind | 56 | Not recorded | 68fa74eb1e209131cea64bbf | | InterMind | 55.6 | Not recorded | 68fa74eb1e209131cea64bbf | | Baichuan2-7b | 40 | Not recorded | 68fa74eb1e209131cea64bbf | | Chatglm3-6b | 39.5 | Not recorded | 68fa74eb1e209131cea64bbf | | BiLSTM | 38.1 | Not recorded | 68fa74eb1e209131cea64bbf | | RoBerta | 37.5 | Not recorded | 68fa74eb1e209131cea64bbf | | Llama2-Chinese-7b | 35.4 | Not recorded | 68fa74eb1e209131cea64bbf | ### GPT-4 Precision (Normal): 78.6. Result ID: 69afe08e6dbb7075b958777c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ChineseMentalBert Precision (Normal): 66.7. Result ID: 69afe08e6dbb7075b958777f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### InterMind Precision (Normal): 66.7. Result ID: 69afe08e6dbb7075b9587780. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Source":"Patient"}. This record does not assert independent reproduction. ### InterMind Precision (Normal): 56. Result ID: 69afe08e6dbb7075b9587782. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Source":"Both"}. This record does not assert independent reproduction. ### InterMind Precision (Normal): 55.6. Result ID: 69afe08e6dbb7075b9587781. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Input Source":"Family"}. This record does not assert independent reproduction. ### Baichuan2-7b Precision (Normal): 40. Result ID: 69afe08e6dbb7075b958777b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Chatglm3-6b Precision (Normal): 39.5. Result ID: 69afe08e6dbb7075b9587779. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BiLSTM Precision (Normal): 38.1. Result ID: 69afe08e6dbb7075b958777d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RoBerta Precision (Normal): 37.5. Result ID: 69afe08e6dbb7075b958777e. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Llama2-Chinese-7b Precision (Normal): 35.4. Result ID: 69afe08e6dbb7075b958777a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.