Classification on Medical (F1-score)
76.6F1 ScoreAKG
Evaluation Results
| Method | Links | |
|---|---|---|
| AKGModel=GPT-4o, Model Size Category=Large models2026.05 | 76.6 | |
| AKGSModel=GPT-4o, Model Size Category=Large models2026.05 | 73.8 | |
| AGModel=LLaMA 3.3-70B, Model Size Category=Large models2026.05 | 70.4 | |
| AGSModel=LLaMA 3.3-70B, Model Size Category=Large models2026.05 | 68.4 | |
| AKGModel=LLaMA 3.3-70B, Model Size Category=Large models2026.05 | 65.2 | |
| AKGSModel=LLaMA 3.3-70B, Model Size Category=Large models2026.05 | 59.9 | |
| BaseModel=N/A, Reference=Sarkar et al., 20232026.05 | 59.4 | |
| AKGModel=LLaMA 3.1-8B, Model Size Category=Medium size models2026.05 | 49.6 | |
| AGModel=DS-R1 1.5B, Model Size Category=Smaller models2026.05 | 48.7 | |
| AKGSModel=LLaMA 3.1-8B, Model Size Category=Medium size models2026.05 | 42.4 |