# T2I Metric Evaluation on CROCsyn Forward Text-Based Source: [T2I Metric Evaluation on CROCsyn Forward Text-Based]() Collection index: [llms.txt]() Data updated: 2026-04-21T10:45:48.245Z Evaluation of Text-to-Image (T2I) generation metrics, specifically measuring Scaled Accuracy, using the CROCsyn Forward Text-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 Text-Based | | Metric | Scaled Accuracy | | Unit | SCALAR | | 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: SCALAR. ## Recorded results | Method | Scaled Accuracy | Result date | Report paper | | --- | --- | --- | --- | | VQAScore | 0.968 | Not recorded | 68fa789f1e209131cea796a5 | | AlignScore | 0.922 | Not recorded | 68fa789f1e209131cea796a5 | | BLIP2-ITM | 0.883 | Not recorded | 68fa789f1e209131cea796a5 | | BVQA | 0.868 | Not recorded | 68fa789f1e209131cea796a5 | | PickScore | 0.796 | Not recorded | 68fa789f1e209131cea796a5 | | VQAScore | 0.552 | Not recorded | 68fa789f1e209131cea796a5 | | VQAScore | 0.442 | Not recorded | 68fa789f1e209131cea796a5 | | AlignScore | 0.044 | Not recorded | 68fa789f1e209131cea796a5 | | BLIP2-ITM | 0.041 | Not recorded | 68fa789f1e209131cea796a5 | | PickScore | 0.039 | Not recorded | 68fa789f1e209131cea796a5 | | AlignScore | 0.022 | Not recorded | 68fa789f1e209131cea796a5 | | PickScore | 0.004 | Not recorded | 68fa789f1e209131cea796a5 | | BVQA | -0.017 | Not recorded | 68fa789f1e209131cea796a5 | | BVQA | -0.034 | Not recorded | 68fa789f1e209131cea796a5 | | BLIP2-ITM | -0.037 | Not recorded | 68fa789f1e209131cea796a5 | | CLIPScore | -0.214 | Not recorded | 68fa789f1e209131cea796a5 | | CLIPScore | -0.308 | Not recorded | 68fa789f1e209131cea796a5 | | CLIPScore | -0.309 | Not recorded | 68fa789f1e209131cea796a5 | ### VQAScore Scaled Accuracy: 0.968. Result ID: 69e754d647f34ce924ce5ada. [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. ### AlignScore Scaled Accuracy: 0.922. Result ID: 69e754d647f34ce924ce5ad5. [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. ### BLIP2-ITM Scaled Accuracy: 0.883. Result ID: 69e754d647f34ce924ce5ad6. [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. ### BVQA Scaled Accuracy: 0.868. Result ID: 69e754d647f34ce924ce5ad9. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type (P)":"entity placement (EP)","Metric Category":"VQA-based"}. This record does not assert independent reproduction. ### PickScore Scaled Accuracy: 0.796. Result ID: 69e754d647f34ce924ce5ad8. [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. ### VQAScore Scaled Accuracy: 0.552. Result ID: 69e754d647f34ce924ce5ad4. [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. ### VQAScore Scaled Accuracy: 0.442. Result ID: 69e754d647f34ce924ce5ae0. [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. ### AlignScore Scaled Accuracy: 0.044. Result ID: 69e754d647f34ce924ce5adb. [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. ### BLIP2-ITM Scaled Accuracy: 0.041. Result ID: 69e754d647f34ce924ce5adc. [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. ### PickScore Scaled Accuracy: 0.039. Result ID: 69e754d647f34ce924ce5ad2. [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: 0.022. Result ID: 69e754d647f34ce924ce5acf. [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. ### PickScore Scaled Accuracy: 0.004. Result ID: 69e754d647f34ce924ce5ade. [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. ### BVQA Scaled Accuracy: -0.017. Result ID: 69e754d647f34ce924ce5ad3. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type (P)":"entity variation (EV)","Metric Category":"VQA-based"}. This record does not assert independent reproduction. ### BVQA Scaled Accuracy: -0.034. Result ID: 69e754d647f34ce924ce5adf. [Reporting 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: -0.037. Result ID: 69e754d647f34ce924ce5ad0. [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. ### CLIPScore Scaled Accuracy: -0.214. Result ID: 69e754d647f34ce924ce5ad7. [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. ### CLIPScore Scaled Accuracy: -0.308. Result ID: 69e754d647f34ce924ce5ad1. [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: -0.309. Result ID: 69e754d647f34ce924ce5add. [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. Page 1 of 1. This is an index page, not the full collection.