InterleaveThinker: Reinforcing Agentic Interleaved Generation

Benchmark Model Rank Results
image-editing-on-risebenchInterleaveThinker + Qwen-Image-Edit-2511#3RISEBench Overall Accuracy: 30.0
image-generation-on-wiseInterleaveThinker + FLUX.2-klein-9B#11Overall: 0.73