# Robot Manipulation on LIBERO LONG (test) Source: [Robot Manipulation on LIBERO LONG (test)]() Collection index: [llms.txt]() Data updated: 2026-05-12T09:49:09.639Z Evaluation of robot manipulation performance using the LIBERO LONG test set, focusing on success rate metrics. 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 | Robot Manipulation | | Dataset (including any stated split) | LIBERO LONG (test) | | Metric | Success Rate | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 27 of 27 | | 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](): Higher is better; unit: PERCENT. - [SR (Put soup and box in basket)](): Higher is better; unit: PERCENT. - [SR (Put box and butter in basket)](): Higher is better; unit: PERCENT. - [SR (Turn on stove and put pot)](): Higher is better; unit: PERCENT. - [SR (Put bowl in drawer and close)](): Higher is better; unit: PERCENT. - [SR (Put mugs on left and right plates)](): Higher is better; unit: PERCENT. - [SR (Pick book and place it in back)](): Higher is better; unit: PERCENT. - [SR (Put mug on plate, pudding right)](): Higher is better; unit: PERCENT. - [SR (Put soup and sauce in basket)](): Higher is better; unit: PERCENT. - [SR (Put both pots on stove)](): Higher is better; unit: PERCENT. - [SR (Put mug in microwave and close)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Success Rate | Result date | Report paper | | --- | --- | --- | --- | | ElasticFlow | 97.6 | Not recorded | 6a02b402dbc836b87d8245c8 | | HiF-VLA | 96.4 | Not recorded | 693a50316cfd488761a54c65 | | HiF-VLA | 96.4 | Not recorded | 6a02b402dbc836b87d8245c8 | | ElasticFlow | 95.6 | Not recorded | 6a02b402dbc836b87d8245c8 | | HiF-VLA | 94.4 | Not recorded | 693a50316cfd488761a54c65 | | HiF-VLA | 94.4 | Not recorded | 6a02b402dbc836b87d8245c8 | | OpenVLA-OFT\* | 94 | Not recorded | 693a50316cfd488761a54c65 | | OpenVLA-OFT | 94 | Not recorded | 6a02b402dbc836b87d8245c8 | | MemoryVLA | 93.4 | Not recorded | 693a50316cfd488761a54c65 | | MemoryVLA | 93.4 | Not recorded | 6a02b402dbc836b87d8245c8 | | OpenVLA-OFT\* | 91 | Not recorded | 693a50316cfd488761a54c65 | | OpenVLA-OFT | 91 | Not recorded | 6a02b402dbc836b87d8245c8 | | UniVLA\* | 90 | Not recorded | 693a50316cfd488761a54c65 | | UniVLA | 90 | Not recorded | 6a02b402dbc836b87d8245c8 | | Seer | 87.7 | Not recorded | 693a50316cfd488761a54c65 | | Seer | 87.7 | Not recorded | 6a02b402dbc836b87d8245c8 | | Seer (scratch) | 78.7 | Not recorded | 693a50316cfd488761a54c65 | | Seer (scratch) | 78.7 | Not recorded | 6a02b402dbc836b87d8245c8 | | Dita | 77.9 | Not recorded | 68fa7b201e209131cea86b67 | | Dita | 63.8 | Not recorded | 68fa7b201e209131cea86b67 | | UniVLA\* | 63 | Not recorded | 693a50316cfd488761a54c65 | | UniVLA | 63 | Not recorded | 6a02b402dbc836b87d8245c8 | | OpenVLA | 54 | Not recorded | 693a50316cfd488761a54c65 | | OpenVLA | 54 | Not recorded | 6a02b402dbc836b87d8245c8 | | OpenVLA | 53.7 | Not recorded | 68fa7b201e209131cea86b67 | | Octo | 51.1 | Not recorded | 68fa7b201e209131cea86b67 | | Diffusion Policy | 50.5 | Not recorded | 68fa7b201e209131cea86b67 | ### ElasticFlow Success Rate: 97.6. Result ID: 6a02f79547f34ce924e62876. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy inputs":"third-person image, wrist-view image, language instruction","Official reproduction":"false"}. This record does not assert independent reproduction. ### HiF-VLA Success Rate: 96.4. Result ID: 6999eec65698665ec46f8699. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Policy inputs":"third-person image, wrist-view image, language instruction"}. This record does not assert independent reproduction. ### HiF-VLA Success Rate: 96.4. Result ID: 6a02f79547f34ce924e62875. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Policy inputs":"third-person image, wrist-view image, language instruction","Official reproduction":"false"}. This record does not assert independent reproduction. ### ElasticFlow Success Rate: 95.6. Result ID: 6a02f79547f34ce924e62870. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Official reproduction":"false"}. This record does not assert independent reproduction. ### HiF-VLA Success Rate: 94.4. Result ID: 6999eec65698665ec46f8694. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Policy inputs":"third-view image, language instruction"}. This record does not assert independent reproduction. ### HiF-VLA Success Rate: 94.4. Result ID: 6a02f79547f34ce924e6286f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Official reproduction":"false"}. This record does not assert independent reproduction. ### OpenVLA-OFT\* Success Rate: 94. Result ID: 6999eec65698665ec46f8698. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy inputs":"third-person image, wrist-view image, language instruction"}. This record does not assert independent reproduction. ### OpenVLA-OFT Success Rate: 94. Result ID: 6a02f79547f34ce924e62874. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy inputs":"third-person image, wrist-view image, language instruction","Official reproduction":"true"}. This record does not assert independent reproduction. ### MemoryVLA Success Rate: 93.4. Result ID: 6999eec65698665ec46f8692. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy inputs":"third-view image, language instruction"}. This record does not assert independent reproduction. ### MemoryVLA Success Rate: 93.4. Result ID: 6a02f79547f34ce924e6286d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Official reproduction":"false"}. This record does not assert independent reproduction. ### OpenVLA-OFT\* Success Rate: 91. Result ID: 6999eec65698665ec46f8693. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy inputs":"third-view image, language instruction"}. This record does not assert independent reproduction. ### OpenVLA-OFT Success Rate: 91. Result ID: 6a02f79547f34ce924e6286e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Official reproduction":"true"}. This record does not assert independent reproduction. ### UniVLA\* Success Rate: 90. Result ID: 6999eec65698665ec46f8697. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy inputs":"third-person image, wrist-view image, language instruction"}. This record does not assert independent reproduction. ### UniVLA Success Rate: 90. Result ID: 6a02f79547f34ce924e62873. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Policy inputs":"third-person image, wrist-view image, language instruction","Official reproduction":"true"}. This record does not assert independent reproduction. ### Seer Success Rate: 87.7. Result ID: 6999eec65698665ec46f8696. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy inputs":"third-person image, wrist-view image, language instruction"}. This record does not assert independent reproduction. ### Seer Success Rate: 87.7. Result ID: 6a02f79547f34ce924e62872. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy inputs":"third-person image, wrist-view image, language instruction","Official reproduction":"false"}. This record does not assert independent reproduction. ### Seer (scratch) Success Rate: 78.7. Result ID: 6999eec65698665ec46f8695. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy inputs":"third-person image, wrist-view image, language instruction"}. This record does not assert independent reproduction. ### Seer (scratch) Success Rate: 78.7. Result ID: 6a02f79547f34ce924e62871. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy inputs":"third-person image, wrist-view image, language instruction","Official reproduction":"false"}. This record does not assert independent reproduction. ### Dita Success Rate: 77.9. Result ID: 698b81fd7a967eddb76f29eb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training dataset":"Droid"}. This record does not assert independent reproduction. ### Dita Success Rate: 63.8. Result ID: 698b81fd7a967eddb76f29ea. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training dataset":"OXE"}. This record does not assert independent reproduction. ### UniVLA\* Success Rate: 63. Result ID: 6999eec65698665ec46f8691. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy inputs":"third-view image, language instruction"}. This record does not assert independent reproduction. ### UniVLA Success Rate: 63. Result ID: 6a02f79547f34ce924e6286c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Official reproduction":"true"}. This record does not assert independent reproduction. ### OpenVLA Success Rate: 54. Result ID: 6999eec65698665ec46f8690. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Policy inputs":"third-view image, language instruction"}. This record does not assert independent reproduction. ### OpenVLA Success Rate: 54. Result ID: 6a02f79547f34ce924e6286b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Official reproduction":"false"}. This record does not assert independent reproduction. ### OpenVLA Success Rate: 53.7. Result ID: 698b81fd7a967eddb76f29e9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Octo Success Rate: 51.1. Result ID: 698b81fd7a967eddb76f29e8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Diffusion Policy Success Rate: 50.5. Result ID: 698b81fd7a967eddb76f29e7. [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.