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

TF-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Research Proposal GenerationTF-Bench
Novelty4.328
5
Research Proposal EvaluationTF-Bench (OVERALL)
Novelty Score4.25
2
Research Proposal EvaluationTF-Bench RELATED
Novelty Score4.172
2
Showing 3 of 3 rows