# Generative Commonsense Reasoning on CommonGen V1.0 (test)

Source: [Generative Commonsense Reasoning on CommonGen V1.0 (test)](<https://www.sota2.com/research/sota/generative-commonsense-reasoning-on-commongen-v1-0-test>)

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

Data updated: 2026-02-26T05:37:18.208Z

Evaluation of generative commonsense reasoning capabilities using the test split of the CommonGen V1.0 dataset, typically assessed using generation metrics like BLEU, METEOR, ROUGE, CIDEr, and SPICE.

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 | Generative Commonsense Reasoning |
| Dataset (including any stated split) | CommonGen V1.0 (test) |
| Metric | BLEU-4 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [BLEU-4](<https://www.sota2.com/research/sota/generative-commonsense-reasoning-on-commongen-v1-0-test.md?metric=BLEU-4>): Higher is better; unit: PERCENT.

- [METEOR](<https://www.sota2.com/research/sota/generative-commonsense-reasoning-on-commongen-v1-0-test.md?metric=METEOR>): Higher is better; unit: PERCENT.

- [ROUGE-L](<https://www.sota2.com/research/sota/generative-commonsense-reasoning-on-commongen-v1-0-test.md?metric=ROUGE-L>): Higher is better; unit: PERCENT.

- [CIDEr](<https://www.sota2.com/research/sota/generative-commonsense-reasoning-on-commongen-v1-0-test.md?metric=CIDEr>): Higher is better; unit: PERCENT.

- [SPICE](<https://www.sota2.com/research/sota/generative-commonsense-reasoning-on-commongen-v1-0-test.md?metric=SPICE>): Higher is better; unit: PERCENT.

## Recorded results

| Method | BLEU-4 | Result date | Report paper |
| --- | --- | --- | --- |
| MORE | 32.78 | Not recorded | 68fa73a51e209131cea5da67 |
| MORE | 32.37 | Not recorded | 68fa73a51e209131cea5da67 |
| MORE | 32.29 | Not recorded | 68fa73a51e209131cea5da67 |
| MORE | 32.03 | Not recorded | 68fa73a51e209131cea5da67 |
| BLIP-2 | 31.92 | Not recorded | 68fa73a51e209131cea5da67 |
| OPT | 31.53 | Not recorded | 68fa73a51e209131cea5da67 |
| T5 | 31.16 | Not recorded | 68fa73a51e209131cea5da67 |
| MORE | 30.27 | Not recorded | 68fa73a51e209131cea5da67 |
| MORE | 29.98 | Not recorded | 68fa73a51e209131cea5da67 |
| MORE | 29.87 | Not recorded | 68fa73a51e209131cea5da67 |
| T5 | 28.93 | Not recorded | 68fa73a51e209131cea5da67 |
| GPT-3.5 | 28.91 | Not recorded | 68fa73a51e209131cea5da67 |
| FiD | 28.32 | Not recorded | 68fa73a51e209131cea5da67 |
| ViSCTG | 27.67 | Not recorded | 68fa73a51e209131cea5da67 |
| Prepend | 26.68 | Not recorded | 68fa73a51e209131cea5da67 |
| GPT-3.5 | 21.44 | Not recorded | 68fa73a51e209131cea5da67 |

### MORE

BLEU-4: 32.78. Result ID: 6992fc5b3a6c31484912deb8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

Implementation

Recorded evaluation configuration: {"Backbone":"OPT-2.7b","Modality":"multi-modal"}. This record does not assert independent reproduction.

### MORE

BLEU-4: 32.37. Result ID: 6992fc5b3a6c31484912deb4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

Implementation

Recorded evaluation configuration: {"Backbone":"T5-Large","Modality":"image"}. This record does not assert independent reproduction.

### MORE

BLEU-4: 32.29. Result ID: 6992fc5b3a6c31484912deb5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

Implementation

Recorded evaluation configuration: {"Backbone":"T5-Large","Modality":"multi-modal"}. This record does not assert independent reproduction.

### MORE

BLEU-4: 32.03. Result ID: 6992fc5b3a6c31484912deb3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

Implementation

Recorded evaluation configuration: {"Backbone":"T5-Large","Modality":"text"}. This record does not assert independent reproduction.

### BLIP-2

BLEU-4: 31.92. Result ID: 6992fc5b3a6c31484912deb7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fb71e209131cea46fe6.md>)

[Implementation](<https://github.com/salesforce/LAVIS/tree/main/projects/blip2>)

Recorded evaluation configuration: {"Backbone":"OPT-2.7b","Modality":"multi-modal"}. This record does not assert independent reproduction.

### OPT

BLEU-4: 31.53. Result ID: 6992fc5b3a6c31484912deb6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

[Implementation](<https://github.com/facebookresearch/metaseq>)

Recorded evaluation configuration: {"Backbone":"OPT-2.7b"}. This record does not assert independent reproduction.

### T5

BLEU-4: 31.16. Result ID: 6992fc5b3a6c31484912deb2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"Backbone":"T5-Large"}. This record does not assert independent reproduction.

### MORE

BLEU-4: 30.27. Result ID: 6992fc5b3a6c31484912deb1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

Implementation

Recorded evaluation configuration: {"Backbone":"T5-Base","Modality":"multi-modal"}. This record does not assert independent reproduction.

### MORE

BLEU-4: 29.98. Result ID: 6992fc5b3a6c31484912deb0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

Implementation

Recorded evaluation configuration: {"Backbone":"T5-Base","Modality":"image"}. This record does not assert independent reproduction.

### MORE

BLEU-4: 29.87. Result ID: 6992fc5b3a6c31484912deaf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

Implementation

Recorded evaluation configuration: {"Backbone":"T5-Base","Modality":"text"}. This record does not assert independent reproduction.

### T5

BLEU-4: 28.93. Result ID: 6992fc5b3a6c31484912deab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"Backbone":"T5-Base"}. This record does not assert independent reproduction.

### GPT-3.5

BLEU-4: 28.91. Result ID: 6992fc5b3a6c31484912deaa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

Recorded evaluation configuration: {"Shots":"3-shot"}. This record does not assert independent reproduction.

### FiD

BLEU-4: 28.32. Result ID: 6992fc5b3a6c31484912dead.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69381e209131cea20e9a.md>)

[Implementation](<https://www.sota2.com/github.com/facebookresearch/faiss>)

Recorded evaluation configuration: {"Backbone":"T5-Base"}. This record does not assert independent reproduction.

### ViSCTG

BLEU-4: 27.67. Result ID: 6992fc5b3a6c31484912deae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c181e209131cea321ba.md>)

Recorded evaluation configuration: {"Backbone":"T5-Base"}. This record does not assert independent reproduction.

### Prepend

BLEU-4: 26.68. Result ID: 6992fc5b3a6c31484912deac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fe51e209131cea47f64.md>)

[Implementation](<https://github.com/AlexTMallen/adaptive-retrieval>)

Recorded evaluation configuration: {"Backbone":"T5-Base"}. This record does not assert independent reproduction.

### GPT-3.5

BLEU-4: 21.44. Result ID: 6992fc5b3a6c31484912dea9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73a51e209131cea5da67.md>)

Recorded evaluation configuration: {"Shots":"0-shot"}. This record does not assert independent reproduction.

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