ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing
Open paper
Benchmark
Model
Rank
Results
image-editing-on-kris-bench
ThinkRL-Edit
–
KRIS-Bench Overall: 71.65
image-editing-on-risebench
ThinkRL-Edit
–
RISEBench Overall Accuracy: 29.7
Rank counts only results with a code link.