# Commonsense Reasoning on Winograd Schema Challenge (WSC) (test) Source: [Commonsense Reasoning on Winograd Schema Challenge (WSC) (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:27:30.090Z Evaluation of model performance on the test split of the Winograd Schema Challenge dataset for commonsense reasoning, measured by 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 | Commonsense Reasoning | | Dataset (including any stated split) | Winograd Schema Challenge (WSC) (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | HNN | 75.1 | Not recorded | 68fa661c1e209131cea0e664 | | BERTWiki-WSCR | 72.2 | Not recorded | 68fa661c1e209131cea0e664 | | GPT-2 | 70.7 | Not recorded | 68fa661c1e209131cea0e664 | | BERTWSCR | 70.3 | Not recorded | 68fa661c1e209131cea0e664 | | DSSM | 63 | Not recorded | 68fa661c1e209131cea0e664 | | UDSSM-II | 62.4 | Not recorded | 68fa65891e209131cea0ae90 | | BERTLARGE-LM | 62 | Not recorded | 68fa661c1e209131cea0e664 | | Google Language Model | 61.5 | Not recorded | 68fa65891e209131cea0ae90 | | UDSSM-II | 59.2 | Not recorded | 68fa65891e209131cea0ae90 | | UDSSM-I | 57.1 | Not recorded | 68fa65891e209131cea0ae90 | | Google Language Model | 56.4 | Not recorded | 68fa65891e209131cea0ae90 | | UDSSM-I | 54.5 | Not recorded | 68fa65891e209131cea0ae90 | | USSM + Cause-Effect + WordNet + ConceptNet Knowledge Bases | 52.8 | Not recorded | 68fa65891e209131cea0ae90 | | USSM + NKAM + 3 Knowledge Bases | 52.8 | Not recorded | 68fa65891e209131cea0ae90 | | USSM + Cause-Effect Knowledge Base | 52 | Not recorded | 68fa65891e209131cea0ae90 | | ELMo | 51.5 | Not recorded | 68fa65891e209131cea0ae90 | | Co-reference Resolution Tool | 50.5 | Not recorded | 68fa65891e209131cea0ae90 | ### HNN Accuracy: 75.1. Result ID: 698cdb6e8b517eb4331d327d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BERTWiki-WSCR Accuracy: 72.2. Result ID: 698cdb6e8b517eb4331d327b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-2 Accuracy: 70.7. Result ID: 698cdb6e8b517eb4331d327a. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BERTWSCR Accuracy: 70.3. Result ID: 698cdb6e8b517eb4331d327c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DSSM Accuracy: 63. Result ID: 698cdb6e8b517eb4331d3278. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### UDSSM-II Accuracy: 62.4. Result ID: 698cb2a18b517eb4331c243d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ensemble":true}. This record does not assert independent reproduction. ### BERTLARGE-LM Accuracy: 62. Result ID: 698cdb6e8b517eb4331d3279. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Google Language Model Accuracy: 61.5. Result ID: 698cb2a18b517eb4331c243b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"ensemble":true}. This record does not assert independent reproduction. ### UDSSM-II Accuracy: 59.2. Result ID: 698cb2a18b517eb4331c243a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ensemble":false}. This record does not assert independent reproduction. ### UDSSM-I Accuracy: 57.1. Result ID: 698cb2a18b517eb4331c243c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ensemble":true}. This record does not assert independent reproduction. ### Google Language Model Accuracy: 56.4. Result ID: 698cb2a18b517eb4331c2438. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"ensemble":false}. This record does not assert independent reproduction. ### UDSSM-I Accuracy: 54.5. Result ID: 698cb2a18b517eb4331c2439. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ensemble":false}. This record does not assert independent reproduction. ### USSM + Cause-Effect + WordNet + ConceptNet Knowledge Bases Accuracy: 52.8. Result ID: 698cb2a18b517eb4331c2435. [Reporting paper]() Recorded evaluation configuration: {"Knowledge Bases":"Cause-Effect, WordNet, ConceptNet"}. This record does not assert independent reproduction. ### USSM + NKAM + 3 Knowledge Bases Accuracy: 52.8. Result ID: 698cb2a18b517eb4331c2436. [Reporting paper]() Recorded evaluation configuration: {"Knowledge Bases":"3"}. This record does not assert independent reproduction. ### USSM + Cause-Effect Knowledge Base Accuracy: 52. Result ID: 698cb2a18b517eb4331c2434. [Reporting paper]() Recorded evaluation configuration: {"Knowledge Base":"Cause-Effect"}. This record does not assert independent reproduction. ### ELMo Accuracy: 51.5. Result ID: 698cb2a18b517eb4331c2437. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Co-reference Resolution Tool Accuracy: 50.5. Result ID: 698cb2a18b517eb4331c2433. [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.