Dino (STSb/̄🦕)

Reported on 6 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing6 results

Semantic Textual SimilarityonSTS13
Spearman Correlation· 2021-04-15
0.8126
best: 0.9058 (AnglE-LLaMA-7B)
SOTA
Generating Datasets with Pretrained Language Models arXiv:2104.07540
Semantic Textual SimilarityonSTS14
Spearman Correlation· 2021-04-15
0.7125
best: 0.8689 (AnglE-LLaMA-13B)
Generating Datasets with Pretrained Language Models arXiv:2104.07540
Semantic Textual SimilarityonSICK
Spearman Correlation· 2021-04-15
0.6809
best: 0.8243 (PromCSE-RoBERTa-large (0.355B))
Generating Datasets with Pretrained Language Models arXiv:2104.07540
Semantic Textual SimilarityonSTS Benchmark
Spearman Correlation· 2021-04-15
0.7782
best: 0.931 (Mnet-Sim)
Generating Datasets with Pretrained Language Models arXiv:2104.07540
Semantic Textual SimilarityonSTS12
Spearman Correlation· 2021-04-15
0.7027
best: 0.802 (PromptEOL+CSE+OPT-13B)
Generating Datasets with Pretrained Language Models arXiv:2104.07540
Semantic Textual SimilarityonSTS16
Spearman Correlation· 2021-04-15
0.7718
best: 0.87 (AnglE-LLaMA-7B-v2)
Generating Datasets with Pretrained Language Models arXiv:2104.07540