Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Natural Language Understanding on MAC-SLU (Overall Acc, Intent Acc, Slot F1)
Loading...
4.52
Overall Accuracy
SFL-MTSC
1.3896
2.2023
3.015
3.8277
Jun 24, 2026
Overall Accuracy
Intent Accuracy
Slot F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Overall Accuracy
Intent Accuracy
Slot F1 Score
SFL-MTSC
Backbone=Qwen3-4B-Inst...
2026.06
4.52
53.26
52.23
CroPrompt (Slot→Intent)
Backbone=Qwen3-4B-Inst...
2026.06
4.16
55.12
52.7
SFL-MTSC
Backbone=Qwen3-4B-Inst...
2026.06
4.1
56.82
47.33
GPT-SLU
Backbone=Qwen3-4B-Inst...
2026.06
4.07
58.05
49.06
SFL-MTSC
Backbone=Qwen3-4B-Inst...
2026.06
3.3
44.22
58.25
Vanilla Prompting
Backbone=Qwen3-4B-Inst...
2026.06
2.07
46.84
29.39
SFL-MTSC
Backbone=Qwen3-4B-Inst...
2026.06
1.91
46.13
46.24
CroPrompt (Intent→Slot)
Backbone=Qwen3-4B-Inst...
2026.06
1.51
48.84
36.93
Feedback
Search any
task
Search any
task