# Commonsense Plausibility Estimation (Attribute Ranking) on CoDa Source: [Commonsense Plausibility Estimation (Attribute Ranking) on CoDa]() Collection index: [llms.txt]() Data updated: 2026-04-21T10:45:47.705Z Evaluation of model performance on the CoDa dataset, specifically assessing commonsense plausibility by ranking attributes, measured using Spearman's rank correlation coefficient. 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 Plausibility Estimation (Attribute Ranking) | | Dataset (including any stated split) | CoDa | | Metric | Spearman's ρ | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 - [Spearman's ρ](): Higher is better; unit: SCALAR. ## Recorded results | Method | Spearman's ρ | Result date | Report paper | | --- | --- | --- | --- | | EVA-CLIP | 62.87 | Not recorded | 68fa770e1e209131cea70d46 | | Qwen2\_w/ CL | 59.16 | Not recorded | 68fa770e1e209131cea70d46 | | VERA-T5 | 58.93 | Not recorded | 68fa770e1e209131cea70d46 | | Mistral\_w/ CL | 58.54 | Not recorded | 68fa770e1e209131cea70d46 | | CLIP | 58.1 | Not recorded | 68fa770e1e209131cea70d46 | | Qwen2+verbal. | 57.4 | Not recorded | 68fa770e1e209131cea70d46 | | Mistral+likelihood | 51.3 | Not recorded | 68fa770e1e209131cea70d46 | | Qwen2+likelihood | 50.25 | Not recorded | 68fa770e1e209131cea70d46 | | Qwen2\_w/ CL+likelihood | 49.65 | Not recorded | 68fa770e1e209131cea70d46 | | Mistral+verbal. | 46.64 | Not recorded | 68fa770e1e209131cea70d46 | | RoBERTa\_w/ CL | 44.59 | Not recorded | 68fa770e1e209131cea70d46 | | RoBERTa+likelihood | 24.37 | Not recorded | 68fa770e1e209131cea70d46 | | RoBERTa\_w/ CL+likelihood | 23.36 | Not recorded | 68fa770e1e209131cea70d46 | | COMET-Atomic | 22.91 | Not recorded | 68fa770e1e209131cea70d46 | | ACCENT | 10.07 | Not recorded | 68fa770e1e209131cea70d46 | ### EVA-CLIP Spearman's ρ: 62.87. Result ID: 69e7547b47f34ce924ce5957. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Inference Parameters":"695M","Model Category":"VLM","Method Framework":"ComPaSS"}. This record does not assert independent reproduction. ### Qwen2\_w/ CL Spearman's ρ: 59.16. Result ID: 69e7547b47f34ce924ce5955. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Inference Parameters":"7B","Model Category":"LM","Method Framework":"ComPaSS","Contrastive Learning":"Yes"}. This record does not assert independent reproduction. ### VERA-T5 Spearman's ρ: 58.93. Result ID: 69e7547b47f34ce924ce594b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Inference Parameters":"5B","Model Category":"CSM","Method Framework":"Baseline"}. This record does not assert independent reproduction. ### Mistral\_w/ CL Spearman's ρ: 58.54. Result ID: 69e7547b47f34ce924ce5954. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Inference Parameters":"7B","Model Category":"LM","Method Framework":"ComPaSS","Contrastive Learning":"Yes"}. This record does not assert independent reproduction. ### CLIP Spearman's ρ: 58.1. Result ID: 69e7547b47f34ce924ce5956. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Inference Parameters":"124M","Model Category":"VLM","Method Framework":"ComPaSS"}. This record does not assert independent reproduction. ### Qwen2+verbal. Spearman's ρ: 57.4. Result ID: 69e7547b47f34ce924ce5950. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Inference Parameters":"7B","Model Category":"LM","Evaluation Method":"Verbalization","Method Framework":"Baseline"}. This record does not assert independent reproduction. ### Mistral+likelihood Spearman's ρ: 51.3. Result ID: 69e7547b47f34ce924ce594f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Inference Parameters":"7B","Model Category":"LM","Evaluation Method":"Likelihood","Method Framework":"Baseline"}. This record does not assert independent reproduction. ### Qwen2+likelihood Spearman's ρ: 50.25. Result ID: 69e7547b47f34ce924ce5951. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Inference Parameters":"7B","Model Category":"LM","Evaluation Method":"Likelihood","Method Framework":"Baseline"}. This record does not assert independent reproduction. ### Qwen2\_w/ CL+likelihood Spearman's ρ: 49.65. Result ID: 69e7547b47f34ce924ce5952. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Inference Parameters":"7B","Model Category":"LM","Evaluation Method":"Likelihood","Method Framework":"Baseline","Contrastive Learning":"Yes"}. This record does not assert independent reproduction. ### Mistral+verbal. Spearman's ρ: 46.64. Result ID: 69e7547b47f34ce924ce594e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Inference Parameters":"7B","Model Category":"LM","Evaluation Method":"Verbalization","Method Framework":"Baseline"}. This record does not assert independent reproduction. ### RoBERTa\_w/ CL Spearman's ρ: 44.59. Result ID: 69e7547b47f34ce924ce5953. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Inference Parameters":"355M","Model Category":"LM","Method Framework":"ComPaSS","Contrastive Learning":"Yes"}. This record does not assert independent reproduction. ### RoBERTa+likelihood Spearman's ρ: 24.37. Result ID: 69e7547b47f34ce924ce594c. [Reporting paper]() Recorded evaluation configuration: {"Inference Parameters":"355M","Model Category":"LM","Evaluation Method":"Likelihood","Method Framework":"Baseline"}. This record does not assert independent reproduction. ### RoBERTa\_w/ CL+likelihood Spearman's ρ: 23.36. Result ID: 69e7547b47f34ce924ce594d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Inference Parameters":"355M","Model Category":"LM","Evaluation Method":"Likelihood","Method Framework":"Baseline","Contrastive Learning":"Yes"}. This record does not assert independent reproduction. ### COMET-Atomic Spearman's ρ: 22.91. Result ID: 69e7547b47f34ce924ce594a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Inference Parameters":"440M","Model Category":"CSM","Method Framework":"Baseline"}. This record does not assert independent reproduction. ### ACCENT Spearman's ρ: 10.07. Result ID: 69e7547b47f34ce924ce5949. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Inference Parameters":"440M","Model Category":"CSM","Method Framework":"Baseline"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.