SemEval
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
SemEval-8 (Public Holdout (PH))
83.4Micro F1
11
SemEval Laptop 2014 (test)
76.04F1 (All)
11
SemEval Task 2 2026 (test)
0.671Correlation (r)
10
SemEval Task 2 2026 (test)
0.681Correlation (r)
10
SemEval SICI >= 0.70
58.3Accuracy
10
SemEval 2010
37.31F1 Precision
10
SemEval Task 7 Track 2 (MCQ) 2026 (test)
99.54Accuracy
10
SemEval
52.26F1 Score (%)
10
SemEval Subtask 2 2020
0.583Average Score
10
SemEval Task 1 English 2018 (test)
59.1Macro F1
10
SemEval 8 (val)
67.3Micro F1
10
SemEval
57.27Accuracy
10
SemEval 2010 (test)
89.9Precision
10
Semeval Task B Twitter 2017 (Out-of-domain)
83.8Accuracy
10
16res SemEval 2016 (test)
85.25Precision
10
SemEval Laptop 2014 (test)
87.16Accuracy
9
SemEval-2016 Task 13 Environment
8.3Mean Rank (MR)
9
SemEval (test)
0.915Accuracy
9
SemEval Task 17 all-words 2007
72.3F1 (Nouns)
9
SemEval WSI 2010
18V-Measure (All)
9
SemEval-2026 Task 13 Subtask A (train)
99.6Macro F1
8
SemEval Task 13 Subtask A 2026 Official Kaggle (val)
99.6Macro F1
8
SemEval Task 9 Subtask 1 2026 (dev)
80.4POL Performance
8
SemEval Task 4 Track A 2026 (test)
69.25Accuracy
8
SemEval 2016
63.23Accuracy (FR)
8