Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

RISEBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Reasoning Image EditingRISEBench 1.0 (test)
Temporal Score34.1
30
Instruction-based Image EditingRISEBench 49 (test)
Reasoning62.8
27
Interleaved Image-Text GenerationRISEBench
Temporal Coherence34.1
20
Reasoning-aware Image GenerationRiseBench 1.0 (test)
Instruction Reasoning0.77
19
Reasoning-informed Image EditingRISEBench 1.0 (test)
Temporal Reasoning Score54.1
10
Reasoning Logic Image GenerationRISEBench
Instr. Reas.77
9
Image EditingRISEBench
RISE32.8
8
Showing 7 of 7 rows