whatmodel.sh / image / BLIP3o-NEXT-GRPO-Text-3B

BLIP3o-NEXT-GRPO-Text-3B

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

BLIP3o-NEXT-GRPO-Text-3B is an open-weights image model from Salesforce Research. Its published size is 3B parameters. Licence: apache-2.0.

Model information sources

· Weights licence ↗ · Parameter count ↗

Approximate total for BLIP3o-NEXT (AR model + diffusion transformer), per the makers paper; the GitHub README also labels the released weights including GRPO-Text as "Model Weights (3B)" and the repo name ends in -3B.

42.1±3.0comparison only: no current run option verifiedfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

Score within the LMArena text-to-image comparison set only.

$ how it compares

The image models ranked either side of BLIP3o-NEXT-GRPO-Text-3B, out of 197 with a score, then more from Salesforce Research.

#modelscorewhereRAMreleased
130ChronoEdit-14B NVIDIA43±3local~34GB2025-10
131Lumina-Image 2.0 Alpha-VLLM (Shanghai AI Lab)43±4api $0.075/image +local~13GB2025-01
132BLIP3o-NEXT-GRPO-Text-3B Salesforce Research42±3comparison only
133BAGEL ByteDance Seed42±1api $0.10/image +local~12GB2025-05
134Midjourney V6.1 Midjourney42±4comparison only2024-07
more from Salesforce Research
151BLIP3-o 8B Salesforce Research38±3local~41GB2025-05

see all image models · find the ones that fit your machine

$ what it's good at

text to image▁▂▇▇▆▅█▇▂▃▁▁ #99 of 157 * · 96% of its score · 1 test

Beats Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M), VQ-Diffusion (ITHQ), FLUX.1 Kontext [dev] here, though they rank higher overall. Trails Playground v2 (1024px aesthetic) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GenExam (relaxed overall, GPT-5 judge)12.6% ✎▄█▂▂▂▂▆▄·▂·▂ beats 4/16hard · avg 26%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%sharp

$ where to run it

No verified API or download recorded yet · add one

Weights and documentation: huggingface.co/BLIP3o ↗

$ how the score was worked out · GenExam: A Multidisciplinary… 96%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
GenExam: A Multidisciplinary Text-to-Image Exam (arXiv v5)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%CC-BY-4.0
prior · pull toward the middle▇ 4%
weighted average= 42.1

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json