# Robot Task Completion on LIBERO (Success Rate and Wall-Clock Time) Source: [Robot Task Completion on LIBERO (Success Rate and Wall-Clock Time)]() Collection index: [llms.txt]() Data updated: 2026-06-23T09:13:48.218Z Evaluation of robotic task completion performance on the LIBERO dataset, reporting success rates across various criteria (Spatial, Object, Goal, Long) alongside the corresponding Wall-Clock execution times. 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 Task Completion | | Dataset (including any stated split) | LIBERO | | Metric | Success Rate (Mean) | | 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 (Mean)](): Higher is better; unit: PERCENT. - [Success Rate (Spatial)](): Higher is better; unit: PERCENT. - [Success Rate (Object)](): Higher is better; unit: PERCENT. - [Success Rate (Goal)](): Higher is better; unit: PERCENT. - [Success Rate (L-10)](): Higher is better; unit: PERCENT. - [Wall-Clock Time (All) (Spatial)](): Lower is better; unit: TIME. - [Wall-Clock Time (All) (Object)](): Lower is better; unit: TIME. - [Wall-Clock Time (All) (Goal)](): Lower is better; unit: TIME. - [Wall-Clock Time (All) (L-10)](): Lower is better; unit: TIME. - [Wall-Clock Time (All) (Mean)](): Lower is better; unit: TIME. - [Wall-Clock Time (Success) (Spatial)](): Lower is better; unit: TIME. - [Wall-Clock Time (Success) (Object)](): Lower is better; unit: TIME. - [Wall-Clock Time (Success) (Goal)](): Lower is better; unit: TIME. - [Wall-Clock Time (Success) (L-10)](): Lower is better; unit: TIME. - [Wall-Clock Time (Success) (Mean)](): Lower is better; unit: TIME. ## Recorded results | Method | Success Rate (Mean) | Result date | Report paper | | --- | --- | --- | --- | | Premover | 95.1 | Not recorded | 6a0405dadbc836b87d827870 | | Full-prompt | 95 | Not recorded | 6a0405dadbc836b87d827870 | | SemiVLA-GR00T-N1.6 | 94.1 | Not recorded | 6a3a1348206542251d7c7232 | | SemiVLA-π0-FAST | 92 | Not recorded | 6a3a1348206542251d7c7232 | | SigLIP–Gemma | 91.5 | Not recorded | 6a279e2090966ade919bf75d | | SemiVLA-OpenVLA-OFT | 91.2 | Not recorded | 6a3a1348206542251d7c7232 | | PaliGemma-VLA | 90.7 | Not recorded | 6a279e2090966ade919bf75d | | PaliGemma-VLA | 90.1 | Not recorded | 6a279e2090966ade919bf75d | | PaliGemma-VLA | 89.4 | Not recorded | 6a279e2090966ade919bf75d | | SemiVLA-OpenVLA | 89 | Not recorded | 6a3a1348206542251d7c7232 | | GR00T-N1.6-FT | 87.7 | Not recorded | 6a3a1348206542251d7c7232 | | PaliGemma-VLA | 86.9 | Not recorded | 6a279e2090966ade919bf75d | | PaliGemma-VLA | 86.8 | Not recorded | 6a279e2090966ade919bf75d | | LARA-style Align | 86.3 | Not recorded | 6a3a1348206542251d7c7232 | | π0-FAST-FT | 86.1 | Not recorded | 6a3a1348206542251d7c7232 | | LAM-Pseudo | 85.7 | Not recorded | 6a3a1348206542251d7c7232 | | FixMatch-VLA | 85 | Not recorded | 6a3a1348206542251d7c7232 | | MeanTeacher-VLA | 84.6 | Not recorded | 6a3a1348206542251d7c7232 | | OpenVLA-OFT | 84.4 | Not recorded | 6a3a1348206542251d7c7232 | | PaliGemma-VLA | 83.3 | Not recorded | 6a279e2090966ade919bf75d | | PseudoAction-VLA | 83.2 | Not recorded | 6a3a1348206542251d7c7232 | | PaliGemma-VLA | 82.5 | Not recorded | 6a279e2090966ade919bf75d | | PaliGemma-VLA | 81.6 | Not recorded | 6a279e2090966ade919bf75d | | OpenVLA-FT | 81 | Not recorded | 6a3a1348206542251d7c7232 | | OpenVLA Zero-shot | 69.8 | Not recorded | 6a3a1348206542251d7c7232 | | Octo-FT | 69.7 | Not recorded | 6a3a1348206542251d7c7232 | | Naive Premoving | 66.4 | Not recorded | 6a0405dadbc836b87d827870 | ### Premover Success Rate (Mean): 95.1. Result ID: 6a04548247f34ce924eae937. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setting":"Premover"}. This record does not assert independent reproduction. ### Full-prompt Success Rate (Mean): 95. Result ID: 6a04548247f34ce924eae935. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Setting":"Full-prompt"}. This record does not assert independent reproduction. ### SemiVLA-GR00T-N1.6 Success Rate (Mean): 94.1. Result ID: 6a3a4e3afbc373592c358b11. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeled Dl":"10%","Unlabeled Du":"90%"}. This record does not assert independent reproduction. ### SemiVLA-π0-FAST Success Rate (Mean): 92. Result ID: 6a3a4e3afbc373592c358b10. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeled Dl":"10%","Unlabeled Du":"90%"}. This record does not assert independent reproduction. ### SigLIP–Gemma Success Rate (Mean): 91.5. Result ID: 6a27d47bfbc373592c24b2f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage 2 signal":"Action only","Stage 1 init.":"SigLIP–Gemma"}. This record does not assert independent reproduction. ### SemiVLA-OpenVLA-OFT Success Rate (Mean): 91.2. Result ID: 6a3a4e3afbc373592c358b0f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeled Dl":"10%","Unlabeled Du":"90%"}. This record does not assert independent reproduction. ### PaliGemma-VLA Success Rate (Mean): 90.7. Result ID: 6a27d47bfbc373592c24b2f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage 2 signal":"Action only","Stage 1 init.":"w/ Distribution Bridging"}. This record does not assert independent reproduction. ### PaliGemma-VLA Success Rate (Mean): 90.1. Result ID: 6a27d47bfbc373592c24b2fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage 2 signal":"+ MM+ETC","Stage 1 init.":"w/ Distribution Bridging"}. This record does not assert independent reproduction. ### PaliGemma-VLA Success Rate (Mean): 89.4. Result ID: 6a27d47bfbc373592c24b2f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage 2 signal":"Action only","Stage 1 init.":"w/o Distribution Bridging"}. This record does not assert independent reproduction. ### SemiVLA-OpenVLA Success Rate (Mean): 89. Result ID: 6a3a4e3afbc373592c358b0e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeled Dl":"10%","Unlabeled Du":"90%"}. This record does not assert independent reproduction. ### GR00T-N1.6-FT Success Rate (Mean): 87.7. Result ID: 6a3a4e3afbc373592c358b08. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeled Dl":"10%","Unlabeled Du":"0"}. This record does not assert independent reproduction. ### PaliGemma-VLA Success Rate (Mean): 86.9. Result ID: 6a27d47bfbc373592c24b2fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage 2 signal":"+ ETC","Stage 1 init.":"w/o Distribution Bridging"}. This record does not assert independent reproduction. ### PaliGemma-VLA Success Rate (Mean): 86.8. Result ID: 6a27d47bfbc373592c24b2fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage 2 signal":"+ ETC","Stage 1 init.":"w/ Distribution Bridging"}. This record does not assert independent reproduction. ### LARA-style Align Success Rate (Mean): 86.3. Result ID: 6a3a4e3afbc373592c358b0d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeled Dl":"10%","Unlabeled Du":"90%"}. This record does not assert independent reproduction. ### π0-FAST-FT Success Rate (Mean): 86.1. Result ID: 6a3a4e3afbc373592c358b07. [Reporting paper]() Recorded evaluation configuration: {"Labeled Dl":"10%","Unlabeled Du":"0"}. This record does not assert independent reproduction. ### LAM-Pseudo Success Rate (Mean): 85.7. Result ID: 6a3a4e3afbc373592c358b0c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeled Dl":"10%","Unlabeled Du":"90%"}. This record does not assert independent reproduction. ### FixMatch-VLA Success Rate (Mean): 85. Result ID: 6a3a4e3afbc373592c358b0b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeled Dl":"10%","Unlabeled Du":"90%"}. This record does not assert independent reproduction. ### MeanTeacher-VLA Success Rate (Mean): 84.6. Result ID: 6a3a4e3afbc373592c358b0a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Labeled Dl":"10%","Unlabeled Du":"90%"}. This record does not assert independent reproduction. ### OpenVLA-OFT Success Rate (Mean): 84.4. Result ID: 6a3a4e3afbc373592c358b06. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeled Dl":"10%","Unlabeled Du":"0"}. This record does not assert independent reproduction. ### PaliGemma-VLA Success Rate (Mean): 83.3. Result ID: 6a27d47bfbc373592c24b2f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage 2 signal":"+ MM","Stage 1 init.":"w/ Distribution Bridging"}. This record does not assert independent reproduction. ### PseudoAction-VLA Success Rate (Mean): 83.2. Result ID: 6a3a4e3afbc373592c358b09. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeled Dl":"10%","Unlabeled Du":"90%"}. This record does not assert independent reproduction. ### PaliGemma-VLA Success Rate (Mean): 82.5. Result ID: 6a27d47bfbc373592c24b2fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage 2 signal":"+ MM+ETC","Stage 1 init.":"w/o Distribution Bridging"}. This record does not assert independent reproduction. ### PaliGemma-VLA Success Rate (Mean): 81.6. Result ID: 6a27d47bfbc373592c24b2f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Stage 2 signal":"+ MM","Stage 1 init.":"w/o Distribution Bridging"}. This record does not assert independent reproduction. ### OpenVLA-FT Success Rate (Mean): 81. Result ID: 6a3a4e3afbc373592c358b05. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Labeled Dl":"10%","Unlabeled Du":"0"}. This record does not assert independent reproduction. ### OpenVLA Zero-shot Success Rate (Mean): 69.8. Result ID: 6a3a4e3afbc373592c358b03. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Labeled Dl":"0","Unlabeled Du":"0"}. This record does not assert independent reproduction. ### Octo-FT Success Rate (Mean): 69.7. Result ID: 6a3a4e3afbc373592c358b04. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Labeled Dl":"10%","Unlabeled Du":"0"}. This record does not assert independent reproduction. ### Naive Premoving Success Rate (Mean): 66.4. Result ID: 6a04548247f34ce924eae936. [Reporting paper]() Recorded evaluation configuration: {"Setting":"Naive Premoving"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.