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

Gen

Benchmarks

Task NameDataset NameSOTA ResultTrend
Object DetectionGen1 (test)
mAP50.4
36
Object DetectionGen1
mAP50.4
23
Object DetectionGen1
mAP47.9
21
Object DetectionGen1
mAP0.499
17
Vehicle RoutingGen200K
Missed Stops Rate0
14
Vehicle RoutingGen100K
Missed Delivery Rate0
14
Object DetectionGen1
mAP53.5
13
Object DetectionGEN1
Total Energy (mJ)16.5
12
Generative Language TasksGEN benchmark
IFEval93.4
9
GeneralizationGen
Gen Score35.7
8
Zero-shot ReasoningGen5
Accuracy (Zero-shot)59.7
6
Video Nudity ErasureGen
Nudity Rate17.29
6
AI Video DetectionGen-3 Alpha
Total Count56
1
Showing 13 of 13 rows