List your company

Fileinfo Classification on Custom Malware Dataset (test)

81Weighted AccuracyNemotron 3-Super 120B
37.3248.666071.34Jun 1, 2026

Evaluation results

MethodLinks
Nemotron 3-Super 120BProtocol=Off-the-shelf, Sample size=400, Prompting=task-specific2026.0681
Llama-4 Maverick-17BProtocol=Off-the-shelf, Sample size=400, Prompting=task-specific2026.0677
Claude-4.5 SonnetProtocol=Off-the-shelf, Sample size=400, Prompting=task-specific2026.0674
Llama-3.1-8BProtocol=PEFT, Sample size=entire test set, Fine-tuned parameters=115M2026.0639