# Text-to-Video Generation on VBench (Total, Quality, and Detailed Temporal Metrics) Source: [Text-to-Video Generation on VBench (Total, Quality, and Detailed Temporal Metrics)]() Collection index: [llms.txt]() Data updated: 2026-05-15T10:04:40.686Z Evaluation of Text-to-Video Generation models on the VBench dataset, reporting the Total Score, Quality Score, Semantic Score, and detailed consistency/temporal metrics including Temporal Flickering and Temporal Style. 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 | Text-to-Video Generation | | Dataset (including any stated split) | VBench | | Metric | Total Score | | Unit | PERCENT | | 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 - [Total Score](): Higher is better; unit: PERCENT. - [Quality Score](): Higher is better; unit: PERCENT. - [Semantic Score](): Higher is better; unit: PERCENT. - [Subject Consistency](): Higher is better; unit: PERCENT. - [Background Consistency](): Higher is better; unit: PERCENT. - [Temporal Flickering](): Higher is better; unit: PERCENT. - [Motion Smoothness](): Higher is better; unit: PERCENT. - [Dynamic Degree](): Higher is better; unit: PERCENT. - [Temporal Style](): Higher is better; unit: PERCENT. ## Recorded results | Method | Total Score | Result date | Report paper | | --- | --- | --- | --- | | RAVEN + CM-GRPO | 85.46 | Not recorded | 6a06a8cbdbc836b87d82a399 | | RAVEN | 85.15 | Not recorded | 6a06a8cbdbc836b87d82a399 | | Causal Forcing + CM-GRPO | 85.08 | Not recorded | 6a06a8cbdbc836b87d82a399 | | Causal Forcing | 84.96 | Not recorded | 6a06a8cbdbc836b87d82a399 | | Reward Forcing | 84.39 | Not recorded | 6a06a8cbdbc836b87d82a399 | | Self Forcing | 84.27 | Not recorded | 6a06a8cbdbc836b87d82a399 | | Wan 2.1 | 84.26 | Not recorded | 69b0f70f2d603e6de3e45d72 | | Rolling Forcing | 83.25 | Not recorded | 6a06a8cbdbc836b87d82a399 | | LongLive | 83.05 | Not recorded | 6a06a8cbdbc836b87d82a399 | | CausVid | 83.01 | Not recorded | 6a06a8cbdbc836b87d82a399 | | LTX-Video | 80 | Not recorded | 69b0f70f2d603e6de3e45d72 | | FrameDiT-H | 79.12 | Not recorded | 69b0f70f2d603e6de3e45d72 | | OpenSoraPlan 1.1 | 78 | Not recorded | 69b0f70f2d603e6de3e45d72 | | Latte | 77.29 | Not recorded | 69b0f70f2d603e6de3e45d72 | | OpenSoraPlan 1.3 | 77.23 | Not recorded | 69b0f70f2d603e6de3e45d72 | | Lavie | 77.08 | Not recorded | 69b0f70f2d603e6de3e45d72 | ### RAVEN + CM-GRPO Total Score: 85.46. Result ID: 6a06efa247f34ce924ef2399. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"base\_model":"Wan2.1-T2V-1.3B","Stage":"CM-GRPO"}. This record does not assert independent reproduction. ### RAVEN Total Score: 85.15. Result ID: 6a06efa247f34ce924ef2398. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"base\_model":"Wan2.1-T2V-1.3B","initialization":"Causal Forcing"}. This record does not assert independent reproduction. ### Causal Forcing + CM-GRPO Total Score: 85.08. Result ID: 6a06efa247f34ce924ef2397. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"base\_model":"Wan2.1-T2V-1.3B","Stage":"CM-GRPO"}. This record does not assert independent reproduction. ### Causal Forcing Total Score: 84.96. Result ID: 6a06efa247f34ce924ef2396. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"base\_model":"Wan2.1-T2V-1.3B"}. This record does not assert independent reproduction. ### Reward Forcing Total Score: 84.39. Result ID: 6a06efa247f34ce924ef2395. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"base\_model":"Wan2.1-T2V-1.3B"}. This record does not assert independent reproduction. ### Self Forcing Total Score: 84.27. Result ID: 6a06efa247f34ce924ef2394. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Wan2.1-T2V-1.3B"}. This record does not assert independent reproduction. ### Wan 2.1 Total Score: 84.26. Result ID: 69b1341c6dbb7075b95be300. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"2B","Attention Type":"Full 3D"}. This record does not assert independent reproduction. ### Rolling Forcing Total Score: 83.25. Result ID: 6a06efa247f34ce924ef2393. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Wan2.1-T2V-1.3B"}. This record does not assert independent reproduction. ### LongLive Total Score: 83.05. Result ID: 6a06efa247f34ce924ef2392. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Wan2.1-T2V-1.3B"}. This record does not assert independent reproduction. ### CausVid Total Score: 83.01. Result ID: 6a06efa247f34ce924ef2391. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Wan2.1-T2V-1.3B"}. This record does not assert independent reproduction. ### LTX-Video Total Score: 80. Result ID: 69b1341c6dbb7075b95be2ff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"1.9B","Attention Type":"Full 3D"}. This record does not assert independent reproduction. ### FrameDiT-H Total Score: 79.12. Result ID: 69b1341c6dbb7075b95be301. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"1.3B","Attention Type":"Matrix"}. This record does not assert independent reproduction. ### OpenSoraPlan 1.1 Total Score: 78. Result ID: 69b1341c6dbb7075b95be2fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"1B","Attention Type":"Factorized"}. This record does not assert independent reproduction. ### Latte Total Score: 77.29. Result ID: 69b1341c6dbb7075b95be2fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"1B","Attention Type":"Factorized"}. This record does not assert independent reproduction. ### OpenSoraPlan 1.3 Total Score: 77.23. Result ID: 69b1341c6dbb7075b95be2fe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Params":"2.7B","Attention Type":"Full 3D"}. This record does not assert independent reproduction. ### Lavie Total Score: 77.08. Result ID: 69b1341c6dbb7075b95be2fc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Params":"3B","Attention Type":"Factorized"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.