Semantic Categories Assessment on DementiaBank (manual transcripts)
1.59Mean Control Score4o-mini
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| 4o-miniModel Version=GPT-4o-mini, Transcript type=Manual2026.06 | 1.59 | 1.94 | 0.22 | 0.6 | 0.46 | 0.36 | 0.15 | |
| LLaMAModel Version=Llama 3 70B, Transcript type=Manual2026.06 | 1.47 | 1.87 | 0.27 | 0.38 | 0.25 | 0.05 | 0.61 | |
| 4oModel Version=GPT-4o, Transcript type=Manual2026.06 | 1.22 | 1.83 | 0.49 | 0.88 | 0.56 | 0.43 | 0.29 | |
| ClaudeModel Version=Claude 3.5 Sonnet, Transcript type=Manual2026.06 | 0.65 | 1.51 | 1.32 | 1.05 | 0.62 | 0.53 | 0.49 |