# Compositional Video Generation on DCR-Bench (full evaluation set) Source: [Compositional Video Generation on DCR-Bench (full evaluation set)]() Collection index: [llms.txt]() Data updated: 2026-05-08T11:19:40.591Z Evaluation of models on the DCR-Bench full evaluation set, focusing on compositional video generation capabilities using metrics like CLIPScore, CLIP-attr, BLIP, CCS, and CVR. 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 | Compositional Video Generation | | Dataset (including any stated split) | DCR-Bench (full evaluation set) | | Metric | CLIPScore | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [CLIPScore](): Higher is better; unit: SCALAR. - [CLIP-attr](): Higher is better; unit: SCALAR. - [BLIP](): Higher is better; unit: SCALAR. - [CCS](): Higher is better; unit: SCALAR. - [CVR](): Higher is better; unit: SCALAR. ## Recorded results | Method | CLIPScore | Result date | Report paper | | --- | --- | --- | --- | | DCR | 0.3131 | Not recorded | 69fd6e5e5497b3b670c8974e | | Default Completion Repulsion | 0.3131 | Not recorded | 69fd6e5e5497b3b670c8974e | | DCR w/o Schedule | 0.3115 | Not recorded | 69fd6e5e5497b3b670c8974e | | DCR w/o Schedule | 0.3115 | Not recorded | 69fd6e5e5497b3b670c8974e | | DCR w/o Attractor Prompt | 0.3088 | Not recorded | 69fd6e5e5497b3b670c8974e | | DCR w/o Repulsion | 0.3088 | Not recorded | 69fd6e5e5497b3b670c8974e | | DCR w/o Attractor Prompt | 0.3088 | Not recorded | 69fd6e5e5497b3b670c8974e | | DCR w/o Repulsion | 0.3088 | Not recorded | 69fd6e5e5497b3b670c8974e | | HunyuanVideo | 0.3067 | Not recorded | 69fd6e5e5497b3b670c8974e | | HunyuanVideo | 0.3067 | Not recorded | 69fd6e5e5497b3b670c8974e | | Mochi | 0.304 | Not recorded | 69fd6e5e5497b3b670c8974e | | Mochi | 0.304 | Not recorded | 69fd6e5e5497b3b670c8974e | | CogVideoX | 0.2858 | Not recorded | 69fd6e5e5497b3b670c8974e | | CogVideoX | 0.2858 | Not recorded | 69fd6e5e5497b3b670c8974e | | Negative Prompt | 0.2735 | Not recorded | 69fd6e5e5497b3b670c8974e | | Negative Prompt | 0.2735 | Not recorded | 69fd6e5e5497b3b670c8974e | ### DCR CLIPScore: 0.3131. Result ID: 69fdc6c047f34ce924e1afa2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mochi"}. This record does not assert independent reproduction. ### Default Completion Repulsion CLIPScore: 0.3131. Result ID: 69fdc6c047f34ce924e1afaa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Mochi"}. This record does not assert independent reproduction. ### DCR w/o Schedule CLIPScore: 0.3115. Result ID: 69fdc6c047f34ce924e1afa6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mochi"}. This record does not assert independent reproduction. ### DCR w/o Schedule CLIPScore: 0.3115. Result ID: 69fdc6c047f34ce924e1afae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Mochi","Ablation":"w/o Schedule"}. This record does not assert independent reproduction. ### DCR w/o Attractor Prompt CLIPScore: 0.3088. Result ID: 69fdc6c047f34ce924e1afa4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mochi"}. This record does not assert independent reproduction. ### DCR w/o Repulsion CLIPScore: 0.3088. Result ID: 69fdc6c047f34ce924e1afa5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mochi"}. This record does not assert independent reproduction. ### DCR w/o Attractor Prompt CLIPScore: 0.3088. Result ID: 69fdc6c047f34ce924e1afac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Mochi","Ablation":"w/o Attractor Prompt"}. This record does not assert independent reproduction. ### DCR w/o Repulsion CLIPScore: 0.3088. Result ID: 69fdc6c047f34ce924e1afad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Mochi","Ablation":"w/o Repulsion"}. This record does not assert independent reproduction. ### HunyuanVideo CLIPScore: 0.3067. Result ID: 69fdc6c047f34ce924e1afa0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Guidance strategy":"Standard CFG"}. This record does not assert independent reproduction. ### HunyuanVideo CLIPScore: 0.3067. Result ID: 69fdc6c047f34ce924e1afa8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Guidance":"Standard CFG"}. This record does not assert independent reproduction. ### Mochi CLIPScore: 0.304. Result ID: 69fdc6c047f34ce924e1af9f. [Reporting paper]() Recorded evaluation configuration: {"Guidance strategy":"Standard CFG"}. This record does not assert independent reproduction. ### Mochi CLIPScore: 0.304. Result ID: 69fdc6c047f34ce924e1afa7. [Reporting paper]() Recorded evaluation configuration: {"Guidance":"Standard CFG"}. This record does not assert independent reproduction. ### CogVideoX CLIPScore: 0.2858. Result ID: 69fdc6c047f34ce924e1afa1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Guidance strategy":"Standard CFG"}. This record does not assert independent reproduction. ### CogVideoX CLIPScore: 0.2858. Result ID: 69fdc6c047f34ce924e1afa9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Guidance":"Standard CFG"}. This record does not assert independent reproduction. ### Negative Prompt CLIPScore: 0.2735. Result ID: 69fdc6c047f34ce924e1afa3. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mochi","Guidance strategy":"Negative prompt within standard CFG"}. This record does not assert independent reproduction. ### Negative Prompt CLIPScore: 0.2735. Result ID: 69fdc6c047f34ce924e1afab. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Mochi","Guidance":"Negative prompt within standard CFG"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.