# T2I Metric Evaluation on CROCsyn Inverse Text-Based Source: [T2I Metric Evaluation on CROCsyn Inverse Text-Based]() Collection index: [llms.txt]() Data updated: 2026-04-21T10:45:48.282Z Evaluation of Text-to-Image (T2I) metrics, specifically using the Scaled Accuracy score, on the CROCsyn Inverse 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 Inverse 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 | | --- | --- | --- | --- | | AlignScore | 0.904 | Not recorded | 68fa789f1e209131cea796a5 | | BLIP2-ITM | 0.874 | Not recorded | 68fa789f1e209131cea796a5 | | VQAScore | 0.841 | Not recorded | 68fa789f1e209131cea796a5 | | PickScore | 0.737 | Not recorded | 68fa789f1e209131cea796a5 | | BVQA | 0.505 | Not recorded | 68fa789f1e209131cea796a5 | | AlignScore | 0.186 | Not recorded | 68fa789f1e209131cea796a5 | | BLIP2-ITM | 0.019 | Not recorded | 68fa789f1e209131cea796a5 | | AlignScore | -0.032 | Not recorded | 68fa789f1e209131cea796a5 | | PickScore | -0.034 | Not recorded | 68fa789f1e209131cea796a5 | | VQAScore | -0.043 | Not recorded | 68fa789f1e209131cea796a5 | | PickScore | -0.099 | Not recorded | 68fa789f1e209131cea796a5 | | BVQA | -0.1 | Not recorded | 68fa789f1e209131cea796a5 | | BLIP2-ITM | -0.103 | Not recorded | 68fa789f1e209131cea796a5 | | VQAScore | -0.164 | Not recorded | 68fa789f1e209131cea796a5 | | CLIPScore | -0.201 | Not recorded | 68fa789f1e209131cea796a5 | | BVQA | -0.261 | Not recorded | 68fa789f1e209131cea796a5 | | CLIPScore | -0.281 | Not recorded | 68fa789f1e209131cea796a5 | | CLIPScore | -0.383 | Not recorded | 68fa789f1e209131cea796a5 | ### AlignScore Scaled Accuracy: 0.904. Result ID: 69e754d647f34ce924ce5ae7. [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: 0.874. Result ID: 69e754d647f34ce924ce5ae8. [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. ### VQAScore Scaled Accuracy: 0.841. Result ID: 69e754d647f34ce924ce5aec. [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: 0.737. Result ID: 69e754d647f34ce924ce5aea. [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: 0.505. Result ID: 69e754d647f34ce924ce5aeb. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type (P)":"entity placement (EP)","Metric Category":"VQA-based"}. This record does not assert independent reproduction. ### AlignScore Scaled Accuracy: 0.186. Result ID: 69e754d647f34ce924ce5aed. [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: 0.019. Result ID: 69e754d647f34ce924ce5aee. [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: -0.032. Result ID: 69e754d647f34ce924ce5ae1. [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: -0.034. Result ID: 69e754d647f34ce924ce5af0. [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. ### VQAScore Scaled Accuracy: -0.043. Result ID: 69e754d647f34ce924ce5af2. [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. ### PickScore Scaled Accuracy: -0.099. Result ID: 69e754d647f34ce924ce5ae4. [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. ### BVQA Scaled Accuracy: -0.1. Result ID: 69e754d647f34ce924ce5af1. [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: -0.103. Result ID: 69e754d647f34ce924ce5ae2. [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: -0.164. Result ID: 69e754d647f34ce924ce5ae6. [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. ### CLIPScore Scaled Accuracy: -0.201. Result ID: 69e754d647f34ce924ce5ae9. [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: -0.261. Result ID: 69e754d647f34ce924ce5ae5. [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: -0.281. Result ID: 69e754d647f34ce924ce5aef. [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: -0.383. Result ID: 69e754d647f34ce924ce5ae3. [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.