# Image Classification on BloodMNIST Source: [Image Classification on BloodMNIST]() Collection index: [llms.txt]() Data updated: 2026-06-15T07:57:58.177Z Evaluation of Image Classification performance on the BloodMNIST dataset, reporting Top-1 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 | Image Classification | | Dataset (including any stated split) | BloodMNIST | | Metric | Top-1 Accuracy | | 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 - [Top-1 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | No PE | 96.23 | Not recorded | 69cb551b0636e5bf4afc9f29 | | ResNet-18 | 95.97 | Not recorded | 69cb551b0636e5bf4afc9f29 | | RoPE | 95.59 | Not recorded | 69cb551b0636e5bf4afc9f29 | | Learnable PE | 94.48 | Not recorded | 69cb551b0636e5bf4afc9f29 | | LF-CBM | 87.32 | Not recorded | 6a2f8738d33dfb23e783c166 | | VLLM + S2COPE (Ours) | 79.73 | Not recorded | 6a2f8738d33dfb23e783c166 | | LaBo | 62.5 | Not recorded | 6a2f8738d33dfb23e783c166 | | VLLM (Unoptimized) | 55.26 | Not recorded | 6a2f8738d33dfb23e783c166 | | DCLIP | 23.71 | Not recorded | 6a2f8738d33dfb23e783c166 | | TextSpan | 11.04 | Not recorded | 6a2f8738d33dfb23e783c166 | ### No PE Top-1 Accuracy: 96.23. Result ID: 69cb78cc47f34ce924b36fed. [Reporting paper]() Recorded evaluation configuration: {"Positional Encoding":"None"}. This record does not assert independent reproduction. ### ResNet-18 Top-1 Accuracy: 95.97. Result ID: 69cb78cc47f34ce924b36fec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-18"}. This record does not assert independent reproduction. ### RoPE Top-1 Accuracy: 95.59. Result ID: 69cb78cc47f34ce924b36fef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Positional Encoding":"RoPE"}. This record does not assert independent reproduction. ### Learnable PE Top-1 Accuracy: 94.48. Result ID: 69cb78cc47f34ce924b36fee. [Reporting paper]() Recorded evaluation configuration: {"Positional Encoding":"Learnable"}. This record does not assert independent reproduction. ### LF-CBM Top-1 Accuracy: 87.32. Result ID: 6a2fb06afbc373592c2bd3df. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labels":"Required","Architecture":"Qwen3-VL-8B","Evaluation Protocol":"Concept-based linear probing"}. This record does not assert independent reproduction. ### VLLM + S2COPE (Ours) Top-1 Accuracy: 79.73. Result ID: 6a2fb06afbc373592c2bd3e2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labels":"Not Required","Architecture":"Qwen3-VL-8B","Evaluation Protocol":"Concept-based linear probing"}. This record does not assert independent reproduction. ### LaBo Top-1 Accuracy: 62.5. Result ID: 6a2fb06afbc373592c2bd3e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labels":"Required","Architecture":"Qwen3-VL-8B","Evaluation Protocol":"Concept-based linear probing"}. This record does not assert independent reproduction. ### VLLM (Unoptimized) Top-1 Accuracy: 55.26. Result ID: 6a2fb06afbc373592c2bd3e1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labels":"Not Required","Architecture":"Qwen3-VL-8B","Evaluation Protocol":"Concept-based linear probing"}. This record does not assert independent reproduction. ### DCLIP Top-1 Accuracy: 23.71. Result ID: 6a2fb06afbc373592c2bd3de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labels":"Required","Architecture":"Qwen3-VL-8B","Evaluation Protocol":"Concept-based linear probing"}. This record does not assert independent reproduction. ### TextSpan Top-1 Accuracy: 11.04. Result ID: 6a2fb06afbc373592c2bd3dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labels":"Required","Architecture":"Qwen3-VL-8B","Evaluation Protocol":"Concept-based linear probing"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.