Log Anomaly Detection on Spirit
99.98F1 ScoreCLAD
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| CLADParser=false2026.04 | 99.98 | 99.96 | 99.99 | |
| LogRobustParser=true2026.04 | 99.9 | 99.88 | 99.92 | |
| NeuralLogParser=false2026.04 | 99.34 | 98.74 | 99.96 | |
| CNNParser=true2026.04 | 99.16 | 98.37 | 99.96 | |
| DeBERTa-v3Category=Fine-Tuned2026.04 | 95.3 | — | — | |
| RoBERTa-baseCategory=Fine-Tuned2026.04 | 94.1 | — | — | |
| BERT-baseCategory=Fine-Tuned2026.04 | 93.2 | — | — | |
| GPT-4 + SLCP (5-shot)Category=LLM (Prompt), Shot-count=5, Prompting strategy (SLCP)=true2026.04 | 87.9 | — | — | |
| Drain + RFCategory=Traditional2026.04 | 86.4 | — | — | |
| Drain + RF (best)Category=Traditional2026.04 | 86.4 | — | — | |
| GPT-4 (5-shot)Category=LLM (Prompt), Shot-count=5, Prompting strategy (SLCP)=false2026.04 | 85.6 | — | — | |
| GPT-4 + SLCP (zero)Category=LLM (Prompt), Shot-count=0, Prompting strategy (SLCP)=true2026.04 | 84.3 | — | — | |
| Drain + LRCategory=Traditional2026.04 | 83.1 | — | — | |
| Spell + SVMCategory=Traditional2026.04 | 82.7 | — | — | |
| GPT-4 (zero-shot)Category=LLM (Prompt), Shot-count=0, Prompting strategy (SLCP)=false2026.04 | 81.2 | — | — | |
| LLaMA-3 (zero-shot)Category=LLM (Prompt), Shot-count=0, Prompting strategy (SLCP)=false2026.04 | 76.9 | — | — | |
| GPT-3.5 (zero-shot)Category=LLM (Prompt), Shot-count=0, Prompting strategy (SLCP)=false2026.04 | 74.8 | — | — |