# Reward Modeling on Meta-World Button press Source: [Reward Modeling on Meta-World Button press]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:58:53.569Z Evaluation of Reward Modeling performance specifically on the Button Press task within the Meta-World environment, measured by Prediction Accuracy. 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 | Reward Modeling | | Dataset (including any stated split) | Meta-World Button press | | Metric | Prediction Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 28 of 28 | | 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 - [Prediction Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Prediction Accuracy | Result date | Report paper | | --- | --- | --- | --- | | LTriplet | 76.44 | Not recorded | 694cc50853fdd5c36173a87a | | LTriplet | 75.36 | Not recorded | 694cc50853fdd5c36173a87a | | LR3M | 74.42 | Not recorded | 694cc50853fdd5c36173a87a | | LTriplet | 74.29 | Not recorded | 694cc50853fdd5c36173a87a | | LTriplet | 74.15 | Not recorded | 694cc50853fdd5c36173a87a | | LR3M | 73.76 | Not recorded | 694cc50853fdd5c36173a87a | | LTCNtext | 72.24 | Not recorded | 694cc50853fdd5c36173a87a | | LR3M | 72.07 | Not recorded | 694cc50853fdd5c36173a87a | | LR3M | 71.38 | Not recorded | 694cc50853fdd5c36173a87a | | LTCNtext | 70.27 | Not recorded | 694cc50853fdd5c36173a87a | | LTCNtext | 69.63 | Not recorded | 694cc50853fdd5c36173a87a | | LTCNtext | 69.51 | Not recorded | 694cc50853fdd5c36173a87a | | LVIPtext | 57.83 | Not recorded | 694cc50853fdd5c36173a87a | | LVIPtext | 57.09 | Not recorded | 694cc50853fdd5c36173a87a | | LVIPtext + LVIP | 57.09 | Not recorded | 694cc50853fdd5c36173a87a | | LVIPtext | 57.07 | Not recorded | 694cc50853fdd5c36173a87a | | LVIPtext + LVIP | 56.18 | Not recorded | 694cc50853fdd5c36173a87a | | LVIPtext | 56.03 | Not recorded | 694cc50853fdd5c36173a87a | | LLIV | 55.51 | Not recorded | 694cc50853fdd5c36173a87a | | LVIPtext + LVIP | 55.31 | Not recorded | 694cc50853fdd5c36173a87a | | LLIV | 55.29 | Not recorded | 694cc50853fdd5c36173a87a | | LLIV | 54.79 | Not recorded | 694cc50853fdd5c36173a87a | | LLIV | 54.28 | Not recorded | 694cc50853fdd5c36173a87a | | LVIPtext + LVIP | 53.69 | Not recorded | 694cc50853fdd5c36173a87a | | SigLIP2 | 45.15 | Not recorded | 694cc50853fdd5c36173a87a | | SigLIP2 | 44.83 | Not recorded | 694cc50853fdd5c36173a87a | | SigLIP2 | 44.81 | Not recorded | 694cc50853fdd5c36173a87a | | SigLIP2 | 40.5 | Not recorded | 694cc50853fdd5c36173a87a | ### LTriplet Prediction Accuracy: 76.44. Result ID: 69994c515698665ec4b68210. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"Multi view"}. This record does not assert independent reproduction. ### LTriplet Prediction Accuracy: 75.36. Result ID: 69994c515698665ec4b6820d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"View 1"}. This record does not assert independent reproduction. ### LR3M Prediction Accuracy: 74.42. Result ID: 69994c515698665ec4b681fd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Observation View":"View 1"}. This record does not assert independent reproduction. ### LTriplet Prediction Accuracy: 74.29. Result ID: 69994c515698665ec4b6820f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"View 3"}. This record does not assert independent reproduction. ### LTriplet Prediction Accuracy: 74.15. Result ID: 69994c515698665ec4b6820e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"View 2"}. This record does not assert independent reproduction. ### LR3M Prediction Accuracy: 73.76. Result ID: 69994c515698665ec4b68200. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Observation View":"Multi view"}. This record does not assert independent reproduction. ### LTCNtext Prediction Accuracy: 72.24. Result ID: 69994c515698665ec4b681fc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Observation View":"Multi view"}. This record does not assert independent reproduction. ### LR3M Prediction Accuracy: 72.07. Result ID: 69994c515698665ec4b681ff. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Observation View":"View 3"}. This record does not assert independent reproduction. ### LR3M Prediction Accuracy: 71.38. Result ID: 69994c515698665ec4b681fe. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Observation View":"View 2"}. This record does not assert independent reproduction. ### LTCNtext Prediction Accuracy: 70.27. Result ID: 69994c515698665ec4b681fb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Observation View":"View 3"}. This record does not assert independent reproduction. ### LTCNtext Prediction Accuracy: 69.63. Result ID: 69994c515698665ec4b681f9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Observation View":"View 1"}. This record does not assert independent reproduction. ### LTCNtext Prediction Accuracy: 69.51. Result ID: 69994c515698665ec4b681fa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Observation View":"View 2"}. This record does not assert independent reproduction. ### LVIPtext Prediction Accuracy: 57.83. Result ID: 69994c515698665ec4b68204. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"Multi view"}. This record does not assert independent reproduction. ### LVIPtext Prediction Accuracy: 57.09. Result ID: 69994c515698665ec4b68202. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"View 2"}. This record does not assert independent reproduction. ### LVIPtext + LVIP Prediction Accuracy: 57.09. Result ID: 69994c515698665ec4b68205. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"View 1"}. This record does not assert independent reproduction. ### LVIPtext Prediction Accuracy: 57.07. Result ID: 69994c515698665ec4b68201. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"View 1"}. This record does not assert independent reproduction. ### LVIPtext + LVIP Prediction Accuracy: 56.18. Result ID: 69994c515698665ec4b68206. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"View 2"}. This record does not assert independent reproduction. ### LVIPtext Prediction Accuracy: 56.03. Result ID: 69994c515698665ec4b68203. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"View 3"}. This record does not assert independent reproduction. ### LLIV Prediction Accuracy: 55.51. Result ID: 69994c515698665ec4b6820c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"Multi view"}. This record does not assert independent reproduction. ### LVIPtext + LVIP Prediction Accuracy: 55.31. Result ID: 69994c515698665ec4b68208. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"Multi view"}. This record does not assert independent reproduction. ### LLIV Prediction Accuracy: 55.29. Result ID: 69994c515698665ec4b68209. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"View 1"}. This record does not assert independent reproduction. ### LLIV Prediction Accuracy: 54.79. Result ID: 69994c515698665ec4b6820b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"View 3"}. This record does not assert independent reproduction. ### LLIV Prediction Accuracy: 54.28. Result ID: 69994c515698665ec4b6820a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"View 2"}. This record does not assert independent reproduction. ### LVIPtext + LVIP Prediction Accuracy: 53.69. Result ID: 69994c515698665ec4b68207. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"View 3"}. This record does not assert independent reproduction. ### SigLIP2 Prediction Accuracy: 45.15. Result ID: 69994c515698665ec4b681f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"View 1"}. This record does not assert independent reproduction. ### SigLIP2 Prediction Accuracy: 44.83. Result ID: 69994c515698665ec4b681f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"View 3"}. This record does not assert independent reproduction. ### SigLIP2 Prediction Accuracy: 44.81. Result ID: 69994c515698665ec4b681f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"View 2"}. This record does not assert independent reproduction. ### SigLIP2 Prediction Accuracy: 40.5. Result ID: 69994c515698665ec4b681f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Observation View":"Multi view"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.