Image captioning has conventionally relied on reference-based automatic evaluations, where machine captions are compared against captions written by humans. This is in contrast to the reference-free manner in which humans assess caption quality. In this paper, we report the surprising empirical finding that CLIP (Radford et al., 2021), a cross-modal model pretrained on 400M image+caption pairs from the web, can be used for robust automatic evaluation of image captioning without the need for references. Experiments spanning several corpora demonstrate that our new reference-free metric, <PRE_TAG>CLIPScore</POST_TAG>, achieves the highest correlation with human judgements, outperforming existing reference-based metrics like CIDEr and SPICE. Information gain experiments demonstrate that <PRE_TAG>CLIPScore</POST_TAG>, with its tight focus on image-text compatibility, is complementary to existing reference-based metrics that emphasize text-text similarities. Thus, we also present a reference-augmented version, Ref<PRE_TAG><PRE_TAG>CLIPScore</POST_TAG></POST_TAG>, which achieves even higher correlation. Beyond literal description tasks, several case studies reveal domains where <PRE_TAG>CLIPScore</POST_TAG> performs well (clip-art images, alt-text rating), but also where it is relatively weaker in comparison to reference-based metrics, e.g., news captions that require richer contextual knowledge.