Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Vulnerability Discovery on OSS benchmark (371 held-out cases)
Loading...
412
High/Critical Qualified Findings Rate
EVOHUNT (GLM-5.1)
18.88
120.94
223
325.06
Jun 15, 2026
High/Critical Qualified Findings Rate
Target-Matched Findings Rate (371 Cases)
Evidence Tier T1 Count
Evidence Tier T2 Count
Evidence Tier T3 Count
Retained Qualified No-Match Findings Count
Updated 1mo ago
Evaluation Results
Method
Method
Links
High/Critical Qualified Findings Rate
Target-Matched Findings Rate (371 Cases)
Evidence Tier T1 Count
Evidence Tier T2 Count
Evidence Tier T3 Count
Retained Qualified No-Match Findings Count
EVOHUNT (GLM-5.1)
Backbone=GLM-5.1, Cond...
2026.06
412
42
31
8
3
370
Exp Empty GLM
Backbone=GLM-5.1, Cond...
2026.06
247
36
18
0
18
211
Exp OCS GPT
Backbone=GPT-5.4-xhigh...
2026.06
194
34
13
4
17
160
EVOHUNT (GPT-5.4)
Backbone=GPT-5.4-xhigh...
2026.06
120
23
23
0
0
97
Exp Empty GPT
Backbone=GPT-5.4-xhigh...
2026.06
34
6
4
2
0
28
Feedback
Search any
task
Search any
task