Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

CTI

Benchmarks

Task NameDataset NameSOTA ResultTrend
Incident Ticket GenerationCTI Benchmark
Accuracy4.8
15
Defensive Playbook GenCTI Benchmark
BLEU9.2
15
Mitigation–TTP MappingCTI Benchmark
Accuracy6.2
15
Response SummarizationCTI Benchmark
BLEU Score7.2
15
Campaign EscalationCTI Benchmark
AUC7.8
15
Exploit LikelihoodCTI Benchmark
AUC4.5
15
Evidence WeightingCTI Benchmark
BLEU Score12.5
15
Source Reliability ScoringCTI Benchmark
AUC0.032
15
Graph PopulationCTI Benchmark
Accuracy8.8
15
Threat Report AlignmentCTI Benchmark
BLEU Score11.2
15
Malware Family MappingCTI Benchmark
F1 Score8.2
15
Vulnerability LinkingCTI Benchmark
Accuracy7.5
15
Attack InfrastructureCTI Benchmark
F1 Score7.1
15
Adversarial Text GenerationCTI
ASR97
3
Showing 14 of 14 rows