Human Expert Evaluation
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Human Expert Evaluation Medium Tasks
0.89Kappa
3
Human Expert Evaluation Hard
0.914Kappa
2
Human Expert Evaluation 1.0 (Overall)
0.913Kappa
1
Human Expert Evaluation Hard 1.0
0.914Kappa
1
Human Expert Evaluation Easy 1.0
0.95Kappa
1
Human Expert Evaluation (Overall)
0.913Kappa
1