List your company

ResearchFormerly WizWand

Human Judgment

Benchmarks

TaskDatasetSOTA resultTrendResults

Text Generation

Human Judgment

0.78Spearman Correlation (ρ)

5

Image Generation

Human Judgment

0.73Spearman Correlation (ρ)

3

Human Alignment Evaluation

Human Judgment Dataset

0.166Coherence RMSE

3

Query Categorization

Human judgment data

89.8Micro F1

1