Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Domain-specific language task evaluation on CyberMetric
Loading...
86.8
Accuracy
HyTuning
51.856
60.928
70
79.072
Apr 9, 2026
Accuracy
Information Retrieval Score
Updated 9d ago
Evaluation Results
Method
Method
Links
Accuracy
Information Retrieval Score
HyTuning
Backbone=Qwen2.5-14B,...
2026.04
86.8
0.8
Qwen2.5-14B
Backbone=Qwen2.5-14B,...
2026.04
81.8
4.4
HyTuning
Backbone=Qwen2.5-7B, P...
2026.04
78.8
3.8
HyTuning
Backbone=Qwen2.5-3B, P...
2026.04
73.2
6.8
Qwen2.5-7B
Backbone=Qwen2.5-7B, P...
2026.04
70.8
16.4
INTUITOR
Backbone=Qwen2.5-3B, P...
2026.04
70
9.2
RLVR
Backbone=Qwen2.5-3B, P...
2026.04
56
29.8
RLPR
Backbone=Qwen2.5-3B, P...
2026.04
55.8
30.4
HPT
Backbone=Qwen2.5-3B, P...
2026.04
55.8
30.4
Qwen2.5-3B
Backbone=Qwen2.5-3B, P...
2026.04
55.6
30.8
SFT
Backbone=Qwen2.5-3B, P...
2026.04
55.2
29.6
RD
Backbone=Qwen2.5-3B, P...
2026.04
53.2
32.4
Feedback
Search any
task
Search any
task