# Commonsense Plausibility Estimation (Free-form Text) on CFC

Source: [Commonsense Plausibility Estimation (Free-form Text) on CFC](<https://www.sota2.com/research/sota/commonsense-plausibility-estimation-free-form-text-on-cfc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-21T10:45:47.783Z

Evaluation of model performance on the CFC dataset for commonsense plausibility estimation using free-form text responses, measured by 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 (Free-form Text) |
| Dataset (including any stated split) | CFC |
| Metric | Spearman Correlation (ρ) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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 Correlation (ρ)](<https://www.sota2.com/research/sota/commonsense-plausibility-estimation-free-form-text-on-cfc.md?metric=Spearman%20Correlation%20(%CF%81)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Spearman Correlation (ρ) | Result date | Report paper |
| --- | --- | --- | --- |
| Mistral\_w/ CL | 49.01 | Not recorded | 68fa770e1e209131cea70d46 |
| Mistral+likelihood | 47.98 | Not recorded | 68fa770e1e209131cea70d46 |
| Qwen2\_w/ CL | 46.41 | Not recorded | 68fa770e1e209131cea70d46 |
| VERA-T5 | 45.81 | Not recorded | 68fa770e1e209131cea70d46 |
| Qwen2+likelihood | 45.1 | Not recorded | 68fa770e1e209131cea70d46 |
| RoBERTa\_w/ CL | 44.46 | Not recorded | 68fa770e1e209131cea70d46 |
| Qwen2\_w/ CL+likelihood | 43 | Not recorded | 68fa770e1e209131cea70d46 |
| RoBERTa+likelihood | 42.46 | Not recorded | 68fa770e1e209131cea70d46 |
| EVA-CLIP | 41.46 | Not recorded | 68fa770e1e209131cea70d46 |
| RoBERTa\_w/ CL+likelihood | 38.03 | Not recorded | 68fa770e1e209131cea70d46 |
| CLIP | 35.13 | Not recorded | 68fa770e1e209131cea70d46 |
| ACCENT | 35.04 | Not recorded | 68fa770e1e209131cea70d46 |
| Mistral+verbal. | 32.06 | Not recorded | 68fa770e1e209131cea70d46 |
| Qwen2+verbal. | 29.32 | Not recorded | 68fa770e1e209131cea70d46 |

### Mistral\_w/ CL

Spearman Correlation (ρ): 49.01. Result ID: 69e7547b47f34ce924ce5971.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

Recorded evaluation configuration: {"Inference Parameters":"7B","Model Category":"LM","Method Framework":"ComPaSS","Contrastive Learning":"Yes"}. This record does not assert independent reproduction.

### Mistral+likelihood

Spearman Correlation (ρ): 47.98. Result ID: 69e7547b47f34ce924ce596c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d61e209131cea4d909.md>)

[Implementation](<https://github.com/mistralai/mistral-src>)

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

Spearman Correlation (ρ): 46.41. Result ID: 69e7547b47f34ce924ce5972.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

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 Correlation (ρ): 45.81. Result ID: 69e7547b47f34ce924ce5968.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e51e209131cea4dbc7.md>)

Recorded evaluation configuration: {"Inference Parameters":"5B","Model Category":"CSM","Method Framework":"Baseline"}. This record does not assert independent reproduction.

### Qwen2+likelihood

Spearman Correlation (ρ): 45.1. Result ID: 69e7547b47f34ce924ce596e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74bf1e209131cea6378d.md>)

[Implementation](<https://github.com/QwenLM/Qwen2>)

Recorded evaluation configuration: {"Inference Parameters":"7B","Model Category":"LM","Evaluation Method":"Likelihood","Method Framework":"Baseline"}. This record does not assert independent reproduction.

### RoBERTa\_w/ CL

Spearman Correlation (ρ): 44.46. Result ID: 69e7547b47f34ce924ce5970.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

Recorded evaluation configuration: {"Inference Parameters":"355M","Model Category":"LM","Method Framework":"ComPaSS","Contrastive Learning":"Yes"}. This record does not assert independent reproduction.

### Qwen2\_w/ CL+likelihood

Spearman Correlation (ρ): 43. Result ID: 69e7547b47f34ce924ce596f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703b1e209131cea49c20.md>)

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.

### RoBERTa+likelihood

Spearman Correlation (ρ): 42.46. Result ID: 69e7547b47f34ce924ce5969.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

Recorded evaluation configuration: {"Inference Parameters":"355M","Model Category":"LM","Evaluation Method":"Likelihood","Method Framework":"Baseline"}. This record does not assert independent reproduction.

### EVA-CLIP

Spearman Correlation (ρ): 41.46. Result ID: 69e7547b47f34ce924ce5974.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

Recorded evaluation configuration: {"Inference Parameters":"695M","Model Category":"VLM","Method Framework":"ComPaSS"}. This record does not assert independent reproduction.

### RoBERTa\_w/ CL+likelihood

Spearman Correlation (ρ): 38.03. Result ID: 69e7547b47f34ce924ce596a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c9c1e209131cea34e2c.md>)

[Implementation](<https://github.com/princeton-nlp/SimCSE>)

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.

### CLIP

Spearman Correlation (ρ): 35.13. Result ID: 69e7547b47f34ce924ce5973.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

Recorded evaluation configuration: {"Inference Parameters":"124M","Model Category":"VLM","Method Framework":"ComPaSS"}. This record does not assert independent reproduction.

### ACCENT

Spearman Correlation (ρ): 35.04. Result ID: 69e7547b47f34ce924ce5967.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710d1e209131cea4ee43.md>)

[Implementation](<https://github.com/PlusLabNLP/ACCENT>)

Recorded evaluation configuration: {"Inference Parameters":"440M","Model Category":"CSM","Method Framework":"Baseline"}. This record does not assert independent reproduction.

### Mistral+verbal.

Spearman Correlation (ρ): 32.06. Result ID: 69e7547b47f34ce924ce596b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d61e209131cea4d909.md>)

[Implementation](<https://github.com/mistralai/mistral-src>)

Recorded evaluation configuration: {"Inference Parameters":"7B","Model Category":"LM","Evaluation Method":"Verbalization","Method Framework":"Baseline"}. This record does not assert independent reproduction.

### Qwen2+verbal.

Spearman Correlation (ρ): 29.32. Result ID: 69e7547b47f34ce924ce596d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa770e1e209131cea70d46.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74bf1e209131cea6378d.md>)

[Implementation](<https://github.com/QwenLM/Qwen2>)

Recorded evaluation configuration: {"Inference Parameters":"7B","Model Category":"LM","Evaluation Method":"Verbalization","Method Framework":"Baseline"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.