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

GroundBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multi-shot video generationGroundBench
ARC Score0.426
10
Multi-shot Video GenerationGroundBench (40 randomly sampled scripts)
Identity Score4.18
5
Long-form Question AnsweringGroundBench (test)
Faithfulness (Full)87.5
4
Showing 3 of 3 rows