SemEval
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
SemEval Task 13 2013
23.7FNMI
15
SemEval-2026 Task 2 Subtask 1 (dev)
0.67Valence Correlation (r) Composite
14
SemEval 2010 (test)
19F1@5
14
SemEval-2022 Task 2 Idiomatic STS (evaluation)
0.69Spearman Rho (All)
14
SemEval-07 3.0 (dev)
75.2F1 Score
14
Semeval Task 14 2015 (test)
0.817Exact F1
14
Semeval Task 7 2014 (test)
80.74Exact F1
14
SemEval Task 4 2017 (test)
0.732Macro Recall
14
SemEval Task 1 2026 (test)
1,323.7BT Rating
13
SemEval few-shot zero-shot
81.5Accuracy
13
SemEval Task 1 2023
83.08Hits@1
13
SemEval Laptop ISA 2014
82.43F1 Score
13
SemEval Restaurant ISA 2014
79.73F1
13
SemEval English 2015 (test)
81.7F1 (all)
13
SemEval 2007
74.4F1 Score
13
SemEval Task 4 Track B 2026 (test)
68.75Similarity Score
12
SemEval Zero-Shot
65.86Avg Accuracy
12
SemEval Cross-domain AOPE 2014, 2015, 2016 (test)
89.02Average Score
12
SemEval Task3A 2018 (test)
74.6F1 (pos)
12
SemEval Task 13 2015
72.6F1 Score
12
SemEval Task 12 2013
0.672F1 Score
12
SemEval
16Total Count
11
SemEval Subtask 1 2020
68.7Average Accuracy
11
SemEval Restaurant 2014
89.87Accuracy
11
SemEval Task 1 Spanish 2018 (test)
85.9Micro F1
11