Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
APT chain enumeration on APT-BENCH (test)
Loading...
14
Recall
InternVL3.5-2B
9.84
10.92
12
13.08
Jun 17, 2026
Recall
Type Accuracy
Median Timing Error (ΔT)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Recall
Type Accuracy
Median Timing Error (ΔT)
InternVL3.5-2B
Evaluation Protocol=Ze...
2026.06
14
16
67
GPT-4.1
Evaluation Protocol=Ze...
2026.06
13
15
95
InternVL3.5-4B
Evaluation Protocol=Ze...
2026.06
13
15
75
InternVL3.5-8B
Evaluation Protocol=Ze...
2026.06
13
15
80
Gemini 2.5 Flash
Evaluation Protocol=Ze...
2026.06
12
14
110
Qwen3-VL-8B
Evaluation Protocol=Ze...
2026.06
12
14
90
Qwen3-VL-4B
Evaluation Protocol=Ze...
2026.06
11
13
95
Qwen3-VL-2B
Evaluation Protocol=Ze...
2026.06
10
12
100
Feedback
Search any
task
Search any
task