evertyhing

Reported on 32 benchmarks across 1 task

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing32 results

Image Captioningonnocaps near-domain
B1
79.67
best: 88.9 (GIT2, Single Model)
Image Captioningonnocaps near-domain
B2
62.73
best: 75.86 (GIT2, Single Model)
Image Captioningonnocaps near-domain
B3
42.87
best: 58.99 (PaLI)
Image Captioningonnocaps near-domain
B4
24.8
best: 39.98 (PaLI)
Image Captioningonnocaps near-domain
CIDEr
85.89
best: 125.51 (GIT2, Single Model)
Image Captioningonnocaps near-domain
METEOR
26.68
best: 33.47 (PaLI)
Image Captioningonnocaps near-domain
ROUGE-L
55.37
best: 63.99 (PaLI)
Image Captioningonnocaps near-domain
SPICE
12.24
best: 16.11 (GIT2, Single Model)
Image Captioningonnocaps entire
B1
78.92
best: 88.1 (GIT, Single Model)
Image Captioningonnocaps entire
B2
61.6
best: 74.81 (GIT, Single Model)
Image Captioningonnocaps entire
B3
41.52
best: 57.68 (GIT, Single Model)
Image Captioningonnocaps entire
B4
23.52
best: 37.71 (CoCa - Google Brain)
Image Captioningonnocaps entire
CIDEr
86
best: 126.8 (Lyrics)
Image Captioningonnocaps entire
METEOR
26.31
best: 32.5 (GIT, Single Model)
Image Captioningonnocaps entire
ROUGE-L
54.75
best: 63.12 (GIT, Single Model)
Image Captioningonnocaps entire
SPICE
12.1
best: 15.94 (GIT, Single Model)
Image Captioningonnocaps out-of-domain
B1
75.5
best: 86.28 (PaLI)
Image Captioningonnocaps out-of-domain
B2
56.14
best: 71.28 (GIT, Single Model)
Image Captioningonnocaps out-of-domain
B3
34.53
best: 52.66 (GIT, Single Model)
Image Captioningonnocaps out-of-domain
B4
16.69
best: 32 (PaLI)
Image Captioningonnocaps out-of-domain
CIDEr
85.18
best: 126.67 (PaLI)
Image Captioningonnocaps out-of-domain
METEOR
23.69
best: 30.99 (PaLI)
Image Captioningonnocaps out-of-domain
ROUGE-L
51.54
best: 61.35 (PaLI)
Image Captioningonnocaps out-of-domain
SPICE
11.18
best: 15.7 (GIT, Single Model)
Image Captioningonnocaps in-domain
B1
79.58
best: 88.86 (GIT2, Single Model)
Image Captioningonnocaps in-domain
B2
63.09
best: 76.1 (GIT, Single Model)
Image Captioningonnocaps in-domain
B3
43.92
best: 60.53 (GIT, Single Model)
Image Captioningonnocaps in-domain
B4
26.07
best: 41.65 (GIT, Single Model)
Image Captioningonnocaps in-domain
CIDEr
87.86
best: 149.1 (PaLI)
Image Captioningonnocaps in-domain
METEOR
27.97
best: 34.22 (PaLI)
Image Captioningonnocaps in-domain
ROUGE-L
55.88
best: 64.39 (PaLI)
Image Captioningonnocaps in-domain
SPICE
12.6
best: 16.36 (GIT2, Single Model)