| Benchmark | Model | Rank | Results |
|---|---|---|---|
| explanation-generation-on-whoops | BLIP2 FlanT5-XL (Fine-tuned) | – | Human (%): 15 |
| explanation-generation-on-whoops | BLIP2 FlanT5-XXL (Fine-tuned) | – | Human (%): 27 |
| explanation-generation-on-whoops | BLIP2 FlanT5-XXL (Zero-shot) | – | Human (%): 0 |
| explanation-generation-on-whoops | Ground-truth Caption -> GPT3 (Oracle) | – | Human (%): 68 |
| explanation-generation-on-whoops | Predicted Caption -> GPT3 | – | Human (%): 33 |