# Push and Switch on OpenAI Fetch - Push and Switch (3-Push + 3-Switch, test) Source: [Push and Switch on OpenAI Fetch - Push and Switch (3-Push + 3-Switch, test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:04:59.923Z Evaluation of general Push and Switch capabilities using the combined 3-Push and 3-Switch configuration (S+O) test set from the OpenAI Fetch environment, measured by success rate. 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 | Push and Switch | | Dataset (including any stated split) | OpenAI Fetch - Push and Switch 3-Push + 3-Switch (S+O) (test) | | Metric | Success Rate | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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. ## Recorded results | Method | Success Rate | Result date | Report paper | | --- | --- | --- | --- | | DAFT-RL | 80.5 | Not recorded | 68fa701e1e209131cea49261 | | DAFT-RL | 78.3 | Not recorded | 68fa701e1e209131cea49261 | | LRN | 75.1 | Not recorded | 68fa701e1e209131cea49261 | | STOVE | 71.5 | Not recorded | 68fa701e1e209131cea49261 | | SMORL | 69.4 | Not recorded | 68fa701e1e209131cea49261 | | SRICS | 68.5 | Not recorded | 68fa701e1e209131cea49261 | | GNN | 67.2 | Not recorded | 68fa701e1e209131cea49261 | | SMORL | 63.4 | Not recorded | 68fa701e1e209131cea49261 | | NCS | 63.3 | Not recorded | 68fa701e1e209131cea49261 | | SRICS | 53.1 | Not recorded | 68fa701e1e209131cea49261 | | NCS | 52.9 | Not recorded | 68fa701e1e209131cea49261 | | STOVE | 46.3 | Not recorded | 68fa701e1e209131cea49261 | | LRN | 41.8 | Not recorded | 68fa701e1e209131cea49261 | | GNN | 36.2 | Not recorded | 68fa701e1e209131cea49261 | | DeepSets | 32.4 | Not recorded | 68fa701e1e209131cea49261 | | DeepSets | 25.6 | Not recorded | 68fa701e1e209131cea49261 | | Self-attention | 18.3 | Not recorded | 68fa701e1e209131cea49261 | | Self-attention | 11.5 | Not recorded | 68fa701e1e209131cea49261 | ### DAFT-RL Success Rate: 80.5. Result ID: 69911e6f3a6c31484905d37a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### DAFT-RL Success Rate: 78.3. Result ID: 69911e6f3a6c31484905d3b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### LRN Success Rate: 75.1. Result ID: 69911e6f3a6c31484905d382. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### STOVE Success Rate: 71.5. Result ID: 69911e6f3a6c31484905d37f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### SMORL Success Rate: 69.4. Result ID: 69911e6f3a6c31484905d380. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### SRICS Success Rate: 68.5. Result ID: 69911e6f3a6c31484905d37d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### GNN Success Rate: 67.2. Result ID: 69911e6f3a6c31484905d37e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### SMORL Success Rate: 63.4. Result ID: 69911e6f3a6c31484905d3b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### NCS Success Rate: 63.3. Result ID: 69911e6f3a6c31484905d381. [Reporting paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### SRICS Success Rate: 53.1. Result ID: 69911e6f3a6c31484905d3b3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### NCS Success Rate: 52.9. Result ID: 69911e6f3a6c31484905d3b7. [Reporting paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### STOVE Success Rate: 46.3. Result ID: 69911e6f3a6c31484905d3b5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### LRN Success Rate: 41.8. Result ID: 69911e6f3a6c31484905d3b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### GNN Success Rate: 36.2. Result ID: 69911e6f3a6c31484905d3b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### DeepSets Success Rate: 32.4. Result ID: 69911e6f3a6c31484905d37b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### DeepSets Success Rate: 25.6. Result ID: 69911e6f3a6c31484905d3b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### Self-attention Success Rate: 18.3. Result ID: 69911e6f3a6c31484905d37c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. ### Self-attention Success Rate: 11.5. Result ID: 69911e6f3a6c31484905d3b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"input type":"symbolic"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.