SemEval
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
SemEval Task 2 2016 (test)
44.1F1-Diff
8
SemEval
80Micro F1
8
SemEval 2010
43.6V-M
8
Concatenation of SE02, SE03, SE13, SE15 (test)
82.5F1 (Nouns)
8
SEMEVAL real-world noise
81.47Accuracy
8
SemEval (test)
77.4Accuracy (En)
8
SemEval Restaurant 2014
90.86Accuracy
8
SE03 SemEval-2003 (test)
77.4F1 Score
8
SemEval
26.1F1@3
8
SemEval Spanish 2010 (test)
83.9Avg F1
8
SemEval Task 1 English Track 5 2017
0.852Pearson Correlation (R)
8
SemEval Task 1 Spanish 2017 (Track 3)
85.59Pearson R (x100)
8
SemEval-2019 Task 3 (test)
0.738F1 (happy)
8
SemEval Coarse-grained 2007 (all-words)
0.855F1 (Nouns)
8
SemEval 2015
71.7F1 Score
8
SemEval 2013
67.2F1 Score
8
SemEval Task 6 2022 (test)
60.52F1 Score
7
SemEval Task 11 2026 (nested 5-fold cross-val)
94.3Acc
7
SemEval German 2010 (test)
86.4Avg F1
7
SemEval Dutch 2010 (test)
66.6Average F1
7
SemEval Catalan 2010 (test)
83.5Avg F1 Score
7
SemEval Arabic 2017 (test)
67.67Macro F1 Score
7
SemEval-2010 Task 8 single-model (test)
87.1F1 Score
7
SemEval Task 4 Subtask 4 2014 (test)
85.94-way Accuracy
7
SemEval Task 4 Subtask 3 2014 (test)
0.936Precision
7