# Robotic Control on RoboMimic & OGBench (Online Evaluation) Source: [Robotic Control on RoboMimic & OGBench (Online Evaluation)]() Collection index: [llms.txt]() Data updated: 2026-05-13T06:43:23.830Z Evaluation of agent performance on specific robotic control tasks within the combined RoboMimic and OGBench environments under online evaluation settings. 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 | Robotic Control | | Dataset (including any stated split) | RoboMimic & OGBench online evaluation | | Metric | Can Success Rate | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [Can Success Rate](): Higher is better; unit: PERCENT. - [Square Success Rate](): Higher is better; unit: PERCENT. - [Cube DBL T3 Success Rate](): Higher is better; unit: PERCENT. - [Cube DBL T4 Success Rate](): Higher is better; unit: PERCENT. - [Cube TRL T3 Success Rate](): Higher is better; unit: PERCENT. - [Cube TRL T4 Success Rate](): Higher is better; unit: PERCENT. - [Scene T4 Success Rate](): Higher is better; unit: PERCENT. - [Scene T5 Success Rate](): Higher is better; unit: PERCENT. - [HMaze Med T3 Success Rate](): Higher is better; unit: PERCENT. - [HMaze Med T4 Success Rate](): Higher is better; unit: PERCENT. - [AMaze GNT T4 Success Rate](): Higher is better; unit: PERCENT. - [AMaze GNT T5 Success Rate](): Higher is better; unit: PERCENT. - [IQM Success Rate (SR)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Can Success Rate | Result date | Report paper | | --- | --- | --- | --- | | FMQ + QGBS | 97 | Not recorded | 6a0405e6dbc836b87d827970 | | FMQ | 96 | Not recorded | 6a0405e6dbc836b87d827970 | | MVP\* | 92 | Not recorded | 6a0405e6dbc836b87d827970 | | QC | 88 | Not recorded | 6a0405e6dbc836b87d827970 | | MVP + QGBS | 87 | Not recorded | 6a0405e6dbc836b87d827970 | | MVP | 83 | Not recorded | 6a0405e6dbc836b87d827970 | ### FMQ + QGBS Can Success Rate: 97. Result ID: 6a041c4147f34ce924e96b37. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_algorithm":"FMQ","inference\_algorithm":"QGBS"}. This record does not assert independent reproduction. ### FMQ Can Success Rate: 96. Result ID: 6a041c4147f34ce924e96b36. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_algorithm":"FMQ"}. This record does not assert independent reproduction. ### MVP\* Can Success Rate: 92. Result ID: 6a041c4147f34ce924e96b33. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### QC Can Success Rate: 88. Result ID: 6a041c4147f34ce924e96b32. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MVP + QGBS Can Success Rate: 87. Result ID: 6a041c4147f34ce924e96b35. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"inference\_algorithm":"QGBS"}. This record does not assert independent reproduction. ### MVP Can Success Rate: 83. Result ID: 6a041c4147f34ce924e96b34. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.