Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Natural Language Understanding on QNLI (Exact Match)
Loading...
82.5
Exact Match
AdapShot
17.812
34.606
51.4
68.194
May 5, 2026
Exact Match
Updated 28d ago
Evaluation Results
Method
Method
Links
Exact Match
AdapShot
Backbone=Qwen2.5-7B
2026.05
82.5
DBSA
Backbone=Qwen2.5-7B
2026.05
80.7
Many-shot (256)
Backbone=Qwen2.5-7B
2026.05
78
Many-shot (512)
Backbone=Qwen2.5-7B
2026.05
76.8
Many-shot (1024)
Backbone=Qwen2.5-7B
2026.05
66.7
DBSA
Backbone=LLaMA-3.2 (3B)
2026.05
61.9
Many-shot (512)
Backbone=LLaMA-3.2 (3B)
2026.05
57.9
Many-shot (256)
Backbone=LLaMA-3.2 (3B)
2026.05
55.7
Few-shot (8)
Backbone=Qwen2.5-7B
2026.05
54.1
Many-shot (1024)
Backbone=LLaMA-3.2 (3B)
2026.05
52.6
Few-shot (8)
Backbone=LLaMA-3.2 (3B)
2026.05
51.7
AdapShot
Backbone=LLaMA-3.2 (3B)
2026.05
51.2
Zero-shot
Backbone=LLaMA-3.2 (3B)
2026.05
50.8
Zero-shot
Backbone=Qwen2.5-7B
2026.05
20.3
Feedback
Search any
task
Search any
task