# Subject Recognition on Personalized Subject Recognition 40 subjects 1.0 (test) Source: [Subject Recognition on Personalized Subject Recognition 40 subjects 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:58:09.937Z Evaluation of Subject Recognition performance on the test split of the Personalized Subject Recognition 40 subjects 1.0 dataset, reporting Positive Accuracy, Negative Accuracy, and Weighted Accuracy. 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 | Subject Recognition | | Dataset (including any stated split) | Personalized Subject Recognition 40 subjects 1.0 (test) | | Metric | Positive Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | 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 - [Positive Accuracy](): Higher is better; unit: PERCENT. - [Negative Accuracy](): Higher is better; unit: PERCENT. - [Weighted Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Positive Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Yo'LLaVA | 94.9 | Not recorded | 68fa75fa1e209131cea6ac29 | | GPT-4V + Prompt | 85.1 | Not recorded | 68fa75fa1e209131cea6ac29 | | GPT-4V + Prompt | 80.9 | Not recorded | 68fa75fa1e209131cea6ac29 | | LLaVA + Prompt | 74 | Not recorded | 68fa75fa1e209131cea6ac29 | | LLaVA + Prompt | 73.4 | Not recorded | 68fa75fa1e209131cea6ac29 | | GPT-4V + Prompt | 69.7 | Not recorded | 68fa75fa1e209131cea6ac29 | | GPT-4V + Prompt | 69.6 | Not recorded | 68fa75fa1e209131cea6ac29 | | LLaVA + Prompt | 32 | Not recorded | 68fa75fa1e209131cea6ac29 | | LLaVA | 0 | Not recorded | 68fa75fa1e209131cea6ac29 | ### Yo'LLaVA Positive Accuracy: 94.9. Result ID: 699408d13a6c3148491a8dfa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Type":"Learnable","Number of Tokens":"16"}. This record does not assert independent reproduction. ### GPT-4V + Prompt Positive Accuracy: 85.1. Result ID: 699408d13a6c3148491a8e02. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Type":"Image","Number of Tokens":"~5k"}. This record does not assert independent reproduction. ### GPT-4V + Prompt Positive Accuracy: 80.9. Result ID: 699408d13a6c3148491a8e01. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Type":"Image","Number of Tokens":"~1k"}. This record does not assert independent reproduction. ### LLaVA + Prompt Positive Accuracy: 74. Result ID: 699408d13a6c3148491a8dfe. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Type":"Text","Number of Tokens":"~16"}. This record does not assert independent reproduction. ### LLaVA + Prompt Positive Accuracy: 73.4. Result ID: 699408d13a6c3148491a8dfc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Type":"Human","Number of Tokens":"~16"}. This record does not assert independent reproduction. ### GPT-4V + Prompt Positive Accuracy: 69.7. Result ID: 699408d13a6c3148491a8dff. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Type":"Text","Number of Tokens":"~16"}. This record does not assert independent reproduction. ### GPT-4V + Prompt Positive Accuracy: 69.6. Result ID: 699408d13a6c3148491a8e00. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Type":"Human","Number of Tokens":"~16"}. This record does not assert independent reproduction. ### LLaVA + Prompt Positive Accuracy: 32. Result ID: 699408d13a6c3148491a8dfd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Type":"Text","Number of Tokens":"~1.3k"}. This record does not assert independent reproduction. ### LLaVA Positive Accuracy: 0. Result ID: 699408d13a6c3148491a8dfb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Type":"0","Number of Tokens":"0"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.