# T2I Metric Evaluation on CROCsyn Forward Image-Based Source: [T2I Metric Evaluation on CROCsyn Forward Image-Based]() Collection index: [llms.txt]() Data updated: 2026-04-21T10:45:48.318Z Evaluation of Text-to-Image (T2I) generation metrics, specifically measuring Scaled Accuracy, using the CROCsyn Forward Image-Based dataset. 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 | T2I Metric Evaluation | | Dataset (including any stated split) | CROCsyn Forward Image-Based | | Metric | Scaled Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Scaled Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Scaled Accuracy | Result date | Report paper | | --- | --- | --- | --- | | BLIP2-ITM | 95.9 | Not recorded | 68fa789f1e209131cea796a5 | | AlignScore | 95.8 | Not recorded | 68fa789f1e209131cea796a5 | | VQAScore | 94.6 | Not recorded | 68fa789f1e209131cea796a5 | | PickScore | 90.6 | Not recorded | 68fa789f1e209131cea796a5 | | BVQA | 87.2 | Not recorded | 68fa789f1e209131cea796a5 | | VQAScore | 72 | Not recorded | 68fa789f1e209131cea796a5 | | BLIP2-ITM | 70.6 | Not recorded | 68fa789f1e209131cea796a5 | | AlignScore | 70 | Not recorded | 68fa789f1e209131cea796a5 | | CLIPScore | 66.2 | Not recorded | 68fa789f1e209131cea796a5 | | BVQA | 64.1 | Not recorded | 68fa789f1e209131cea796a5 | | PickScore | 63.7 | Not recorded | 68fa789f1e209131cea796a5 | | BLIP2-ITM | 58.5 | Not recorded | 68fa789f1e209131cea796a5 | | VQAScore | 58 | Not recorded | 68fa789f1e209131cea796a5 | | PickScore | 56.4 | Not recorded | 68fa789f1e209131cea796a5 | | AlignScore | 54.1 | Not recorded | 68fa789f1e209131cea796a5 | | CLIPScore | 45.6 | Not recorded | 68fa789f1e209131cea796a5 | | BVQA | 43.8 | Not recorded | 68fa789f1e209131cea796a5 | | CLIPScore | 40.2 | Not recorded | 68fa789f1e209131cea796a5 | ### BLIP2-ITM Scaled Accuracy: 95.9. Result ID: 69e754d647f34ce924ce5afa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Type (P)":"entity placement (EP)","Metric Category":"Embedding-based"}. This record does not assert independent reproduction. ### AlignScore Scaled Accuracy: 95.8. Result ID: 69e754d647f34ce924ce5af9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt Type (P)":"entity placement (EP)","Metric Category":"Embedding-based"}. This record does not assert independent reproduction. ### VQAScore Scaled Accuracy: 94.6. Result ID: 69e754d647f34ce924ce5afe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt Type (P)":"entity placement (EP)","Metric Category":"VQA-based"}. This record does not assert independent reproduction. ### PickScore Scaled Accuracy: 90.6. Result ID: 69e754d647f34ce924ce5afc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Type (P)":"entity placement (EP)","Metric Category":"Tuned"}. This record does not assert independent reproduction. ### BVQA Scaled Accuracy: 87.2. Result ID: 69e754d647f34ce924ce5afd. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type (P)":"entity placement (EP)","Metric Category":"VQA-based"}. This record does not assert independent reproduction. ### VQAScore Scaled Accuracy: 72. Result ID: 69e754d647f34ce924ce5b04. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt Type (P)":"property variation (PV)","Metric Category":"VQA-based"}. This record does not assert independent reproduction. ### BLIP2-ITM Scaled Accuracy: 70.6. Result ID: 69e754d647f34ce924ce5b00. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Type (P)":"property variation (PV)","Metric Category":"Embedding-based"}. This record does not assert independent reproduction. ### AlignScore Scaled Accuracy: 70. Result ID: 69e754d647f34ce924ce5aff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt Type (P)":"property variation (PV)","Metric Category":"Embedding-based"}. This record does not assert independent reproduction. ### CLIPScore Scaled Accuracy: 66.2. Result ID: 69e754d647f34ce924ce5afb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt Type (P)":"entity placement (EP)","Metric Category":"Embedding-based"}. This record does not assert independent reproduction. ### BVQA Scaled Accuracy: 64.1. Result ID: 69e754d647f34ce924ce5b03. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type (P)":"property variation (PV)","Metric Category":"VQA-based"}. This record does not assert independent reproduction. ### PickScore Scaled Accuracy: 63.7. Result ID: 69e754d647f34ce924ce5b02. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Type (P)":"property variation (PV)","Metric Category":"Tuned"}. This record does not assert independent reproduction. ### BLIP2-ITM Scaled Accuracy: 58.5. Result ID: 69e754d647f34ce924ce5af4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Type (P)":"entity variation (EV)","Metric Category":"Embedding-based"}. This record does not assert independent reproduction. ### VQAScore Scaled Accuracy: 58. Result ID: 69e754d647f34ce924ce5af8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt Type (P)":"entity variation (EV)","Metric Category":"VQA-based"}. This record does not assert independent reproduction. ### PickScore Scaled Accuracy: 56.4. Result ID: 69e754d647f34ce924ce5af6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Type (P)":"entity variation (EV)","Metric Category":"Tuned"}. This record does not assert independent reproduction. ### AlignScore Scaled Accuracy: 54.1. Result ID: 69e754d647f34ce924ce5af3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt Type (P)":"entity variation (EV)","Metric Category":"Embedding-based"}. This record does not assert independent reproduction. ### CLIPScore Scaled Accuracy: 45.6. Result ID: 69e754d647f34ce924ce5b01. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt Type (P)":"property variation (PV)","Metric Category":"Embedding-based"}. This record does not assert independent reproduction. ### BVQA Scaled Accuracy: 43.8. Result ID: 69e754d647f34ce924ce5af7. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type (P)":"entity variation (EV)","Metric Category":"VQA-based"}. This record does not assert independent reproduction. ### CLIPScore Scaled Accuracy: 40.2. Result ID: 69e754d647f34ce924ce5af5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt Type (P)":"entity variation (EV)","Metric Category":"Embedding-based"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.