# Reward Prediction on 10-task benchmark S1 classic Source: [Reward Prediction on 10-task benchmark S1 classic]() Collection index: [llms.txt]() Data updated: 2026-06-11T07:25:18.417Z Evaluation of Reward Prediction performance on the 10-task benchmark S1 classic suite, measured using metrics such as Demo L (MSE). 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 prediction | | Dataset (including any stated split) | 10-task benchmark S1 classic | | Metric | Demo L (MSE) | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 8 of 8 | | 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 - [Demo L (MSE)](): Lower is better; unit: SCALAR. ## Recorded results | Method | Demo L (MSE) | Result date | Report paper | | --- | --- | --- | --- | | SARM2 | 0.006 | Not recorded | 6a28f31990966ade919c15d7 | | SARM2 | 0.01 | Not recorded | 6a28f31990966ade919c15d7 | | SARM2 | 0.01 | Not recorded | 6a28f31990966ade919c15d7 | | SARM2 | 0.025 | Not recorded | 6a28f31990966ade919c15d7 | | RW | 0.026 | Not recorded | 6a28f31990966ade919c15d7 | | Robometer | 0.032 | Not recorded | 6a28f31990966ade919c15d7 | | Robometer | 0.067 | Not recorded | 6a28f31990966ade919c15d7 | | TR | 0.09 | Not recorded | 6a28f31990966ade919c15d7 | ### SARM2 Demo L (MSE): 0.006. Result ID: 6a2a62d3fbc373592c2715fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"standard\_full":"true"}. This record does not assert independent reproduction. ### SARM2 Demo L (MSE): 0.01. Result ID: 6a2a62d3fbc373592c2715fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Multi-Goal":"excluded"}. This record does not assert independent reproduction. ### SARM2 Demo L (MSE): 0.01. Result ID: 6a2a62d3fbc373592c2715fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_subset":"S1"}. This record does not assert independent reproduction. ### SARM2 Demo L (MSE): 0.025. Result ID: 6a2a62d3fbc373592c2715f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Spectral Embedding":"excluded"}. This record does not assert independent reproduction. ### RW Demo L (MSE): 0.026. Result ID: 6a2a62d3fbc373592c2715f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Robometer Demo L (MSE): 0.032. Result ID: 6a2a62d3fbc373592c2715f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"true"}. This record does not assert independent reproduction. ### Robometer Demo L (MSE): 0.067. Result ID: 6a2a62d3fbc373592c2715f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"false"}. This record does not assert independent reproduction. ### TR Demo L (MSE): 0.09. Result ID: 6a2a62d3fbc373592c2715f6. [Reporting paper]() [Method origin paper]() [Implementation]() 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.