Rapidata/Flux-2-pro_t2i_human_preference
Viewer
•
Updated
•
44.9k
•
1.47k
•
8
Luca Strebel
LucStr
AI & ML interests
None yet
Recent Activity
liked
a dataset
25 days ago
Rapidata/Flux-2-pro_t2i_human_preference
liked
a dataset
about 1 month ago
Rapidata/happiness-per-country
reacted
to
jasoncorkill's
post
with 🔥
about 2 months ago
Do you remember https://thispersondoesnotexist.com/ ? It was one of the first cases where the future of generative media really hit us. Humans are incredibly good at recognizing and analyzing faces, so they are a very good litmus test for any generative image model.
But none of the current benchmarks measure the ability of models to generate humans independently. So we built our own. We measure the models ability to generate a diverse set of human faces and using over 20'000 human annotations we ranked all of the major models on their ability to generate faces. Find the full ranking here:
https://app.rapidata.ai/mri/benchmarks/68af24ae74482280b62f7596
We have release the full underlying data publicly here on huggingface: https://huggingface.co/datasets/Rapidata/Face_Generation_Benchmark
Organizations
None yet
liked
a
dataset
25 days ago
liked
a
dataset
about 1 month ago
reacted to
jasoncorkill's
post with 🔥😎🚀
about 2 months ago
Post
4691
Do you remember https://thispersondoesnotexist.com/ ? It was one of the first cases where the future of generative media really hit us. Humans are incredibly good at recognizing and analyzing faces, so they are a very good litmus test for any generative image model.
But none of the current benchmarks measure the ability of models to generate humans independently. So we built our own. We measure the models ability to generate a diverse set of human faces and using over 20'000 human annotations we ranked all of the major models on their ability to generate faces. Find the full ranking here:
https://app.rapidata.ai/mri/benchmarks/68af24ae74482280b62f7596
We have release the full underlying data publicly here on huggingface: Rapidata/Face_Generation_Benchmark
But none of the current benchmarks measure the ability of models to generate humans independently. So we built our own. We measure the models ability to generate a diverse set of human faces and using over 20'000 human annotations we ranked all of the major models on their ability to generate faces. Find the full ranking here:
https://app.rapidata.ai/mri/benchmarks/68af24ae74482280b62f7596
We have release the full underlying data publicly here on huggingface: Rapidata/Face_Generation_Benchmark
liked
3
datasets
about 2 months ago
liked
a
dataset
3 months ago
liked
2
datasets
4 months ago
liked
7
datasets
5 months ago
Rapidata/text-2-video-human-preferences-moonvalley-marey
Viewer
•
Updated
•
1.31k
•
1.17k
•
7
Rapidata/Seedream-3_t2i_human_preference
Viewer
•
Updated
•
60k
•
275
•
12
Rapidata/image-to-video-human-preference-seedance-1-pro
Viewer
•
Updated
•
198
•
397
•
10
Rapidata/image-to-video-human-preference-hailuo-02-marey
Viewer
•
Updated
•
98
•
483
•
11
Rapidata/text-2-video-human-preferences-kling-v2.1-master
Viewer
•
Updated
•
1.19k
•
49
•
9
Rapidata/text-2-video-human-preferences-seedance-1-pro
Viewer
•
Updated
•
1.09k
•
1.24k
•
9
Rapidata/text-2-video-human-preferences-genmo-mochi-1
Viewer
•
Updated
•
1.1k
•
994
•
9
reacted to
jasoncorkill's
post with 😎👀
5 months ago
Post
3278
"Why did the bee get married?"
"Because he found his honey!"
This was the "funniest" joke out of 10'000 jokes we generated with LLMs. With 68% of respondents rating it as "funny".
Original jokes are particularly hard for LLMs, as jokes are very nuanced and a lot of context is needed to understand if something is "funny". Something that can only reliably be measured using humans.
LLMs are not equally good at generating jokes in every language. Generated English jokes turned out to be way funnier than the Japanese ones. 46% of English-speaking voters on average found the generated joke funny. The same statistic for other languages:
Vietnamese: 44%
Portuguese: 40%
Arabic: 37%
Japanese: 28%
There is not much variance in generation quality among models for any fixed language. But still Claude Sonnet 4 slightly outperforms others in Vietnamese, Arabic and Japanese and Gemini 2.5 Flash in Portuguese and English
We have release the 1 Million (!) native speaker ratings and the 10'000 jokes as a dataset for anyone to use:
Rapidata/multilingual-llm-jokes-4o-claude-gemini
"Because he found his honey!"
This was the "funniest" joke out of 10'000 jokes we generated with LLMs. With 68% of respondents rating it as "funny".
Original jokes are particularly hard for LLMs, as jokes are very nuanced and a lot of context is needed to understand if something is "funny". Something that can only reliably be measured using humans.
LLMs are not equally good at generating jokes in every language. Generated English jokes turned out to be way funnier than the Japanese ones. 46% of English-speaking voters on average found the generated joke funny. The same statistic for other languages:
Vietnamese: 44%
Portuguese: 40%
Arabic: 37%
Japanese: 28%
There is not much variance in generation quality among models for any fixed language. But still Claude Sonnet 4 slightly outperforms others in Vietnamese, Arabic and Japanese and Gemini 2.5 Flash in Portuguese and English
We have release the 1 Million (!) native speaker ratings and the 10'000 jokes as a dataset for anyone to use:
Rapidata/multilingual-llm-jokes-4o-claude-gemini
- 7 replies