# Long-horizon Robot Manipulation on CALVIN long-horizon Source: [Long-horizon Robot Manipulation on CALVIN long-horizon]() Collection index: [llms.txt]() Data updated: 2026-04-28T10:34:29.458Z Evaluation of long-horizon robot manipulation capabilities on the CALVIN long-horizon setup, measuring success rates across 5 sequential task steps and average trajectory length. 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 | Long-horizon Robot Manipulation | | Dataset (including any stated split) | CALVIN long-horizon | | Metric | Success Rate 1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Success Rate 1](): Higher is better; unit: PERCENT. - [Success Rate 2](): Higher is better; unit: PERCENT. - [Success Rate 3](): Higher is better; unit: PERCENT. - [Success Rate 4](): Higher is better; unit: PERCENT. - [Success Rate 5](): Higher is better; unit: PERCENT. - [Average Trajectory Length](): Higher is better; unit: SCALAR. ## Recorded results | Method | Success Rate 1 | Result date | Report paper | | --- | --- | --- | --- | | RoboTron-Mani (DiT) | 96.9 | Not recorded | 69f03f8355a3c32af89fa61f | | RoboUniView (default) | 95.4 | Not recorded | 69f03f8355a3c32af89fa61f | | RoboTron-Mani | 94.7 | Not recorded | 69f03f8355a3c32af89fa61f | | LightDP | 93.7 | Not recorded | 69f03f8355a3c32af89fa61f | | MDT (default) | 93.3 | Not recorded | 69f03f8355a3c32af89fa61f | | HULC++ | 93 | Not recorded | 69f03f8355a3c32af89fa61f | | LaDi-WM | 92.7 | Not recorded | 69f03f8355a3c32af89fa61f | | DTP | 92.4 | Not recorded | 69f03f8355a3c32af89fa61f | | DaDu-Corki-SW | 92.3 | Not recorded | 69f03f8355a3c32af89fa61f | | CF-VLA | 91.1 | Not recorded | 69f03f8355a3c32af89fa61f | | TaKSIE | 90.4 | Not recorded | 69f03f8355a3c32af89fa61f | | π\*0.5 | 90.4 | Not recorded | 69f03f8355a3c32af89fa61f | | DySL-VLA | 89.4 | Not recorded | 69f03f8355a3c32af89fa61f | | LCD | 88.7 | Not recorded | 69f03f8355a3c32af89fa61f | | π\*0.5 (NFE=2) | 88.7 | Not recorded | 69f03f8355a3c32af89fa61f | | MIP (π0.5 arch.)\* | 86.7 | Not recorded | 69f03f8355a3c32af89fa61f | | DeeR | 85.3 | Not recorded | 69f03f8355a3c32af89fa61f | ### RoboTron-Mani (DiT) Success Rate 1: 96.9. Result ID: 69f08d2247f34ce924d73b4d. [Reporting paper]() Recorded evaluation configuration: {"Venue":"arXiv","Year":"2025","Aux. Mech.":"3D input","NFE":"\>10"}. This record does not assert independent reproduction. ### RoboUniView (default) Success Rate 1: 95.4. Result ID: 69f08d2247f34ce924d73b49. [Reporting paper]() Recorded evaluation configuration: {"Venue":"arXiv","Year":"2024","Aux. Mech.":"-","NFE":"1"}. This record does not assert independent reproduction. ### RoboTron-Mani Success Rate 1: 94.7. Result ID: 69f08d2247f34ce924d73b47. [Reporting paper]() Recorded evaluation configuration: {"Venue":"ICCV","Year":"2025","Aux. Mech.":"3D input","NFE":"1"}. This record does not assert independent reproduction. ### LightDP Success Rate 1: 93.7. Result ID: 69f08d2247f34ce924d73b4c. [Reporting paper]() Recorded evaluation configuration: {"Venue":"ICCV","Year":"2025","Aux. Mech.":"Distill","NFE":"4"}. This record does not assert independent reproduction. ### MDT (default) Success Rate 1: 93.3. Result ID: 69f08d2247f34ce924d73b4f. [Reporting paper]() Recorded evaluation configuration: {"Venue":"RSS","Year":"2024","Aux. Mech.":"-","NFE":"10"}. This record does not assert independent reproduction. ### HULC++ Success Rate 1: 93. Result ID: 69f08d2247f34ce924d73b46. [Reporting paper]() Recorded evaluation configuration: {"Venue":"ICRA","Year":"2023","Aux. Mech.":"Plan","NFE":"1"}. This record does not assert independent reproduction. ### LaDi-WM Success Rate 1: 92.7. Result ID: 69f08d2247f34ce924d73b4b. [Reporting paper]() Recorded evaluation configuration: {"Venue":"arXiv","Year":"2025","Aux. Mech.":"WM","NFE":"≈4"}. This record does not assert independent reproduction. ### DTP Success Rate 1: 92.4. Result ID: 69f08d2247f34ce924d73b4a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Venue":"RA-L","Year":"2025","Aux. Mech.":"Plan","NFE":"1"}. This record does not assert independent reproduction. ### DaDu-Corki-SW Success Rate 1: 92.3. Result ID: 69f08d2247f34ce924d73b48. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Venue":"ISCA","Year":"2025","Aux. Mech.":"-","NFE":"1"}. This record does not assert independent reproduction. ### CF-VLA Success Rate 1: 91.1. Result ID: 69f08d2247f34ce924d73b52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Venue":"-","Year":"-","Aux. Mech.":"3B","NFE":"2"}. This record does not assert independent reproduction. ### TaKSIE Success Rate 1: 90.4. Result ID: 69f08d2247f34ce924d73b45. [Reporting paper]() Recorded evaluation configuration: {"Venue":"WACV","Year":"2025","Aux. Mech.":"Plan","NFE":"1"}. This record does not assert independent reproduction. ### π\*0.5 Success Rate 1: 90.4. Result ID: 69f08d2247f34ce924d73b4e. [Reporting paper]() Recorded evaluation configuration: {"Venue":"CoRL","Year":"2025","Aux. Mech.":"3B","NFE":"10"}. This record does not assert independent reproduction. ### DySL-VLA Success Rate 1: 89.4. Result ID: 69f08d2247f34ce924d73b44. [Reporting paper]() Recorded evaluation configuration: {"Venue":"DAC","Year":"2026","Aux. Mech.":"-","NFE":"1"}. This record does not assert independent reproduction. ### LCD Success Rate 1: 88.7. Result ID: 69f08d2247f34ce924d73b43. [Reporting paper]() Recorded evaluation configuration: {"Venue":"ICLR","Year":"2024","Aux. Mech.":"Plan","NFE":"1"}. This record does not assert independent reproduction. ### π\*0.5 (NFE=2) Success Rate 1: 88.7. Result ID: 69f08d2247f34ce924d73b51. [Reporting paper]() Recorded evaluation configuration: {"Venue":"CoRL","Year":"2025","Aux. Mech.":"3B","NFE":"2"}. This record does not assert independent reproduction. ### MIP (π0.5 arch.)\* Success Rate 1: 86.7. Result ID: 69f08d2247f34ce924d73b50. [Reporting paper]() Recorded evaluation configuration: {"Venue":"ICLR","Year":"2026","Aux. Mech.":"3B","NFE":"2"}. This record does not assert independent reproduction. ### DeeR Success Rate 1: 85.3. Result ID: 69f08d2247f34ce924d73b42. [Reporting paper]() Recorded evaluation configuration: {"Venue":"NeurIPS","Year":"2024","Aux. Mech.":"-","NFE":"1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.