Table 7B Statistical analysis of LLM performance in treatment scheduling and complex problem solving
Model | Metric | Mean | Standard deviation | Minimum | Maximum |
|---|---|---|---|---|---|
ChatGPT4 | SASTSLLM | 10.02 | 1.23 | 4.5 | 12.00 |
Qwen 2.0 72B | SASTSLLM | 7.89 | 4.46 | 0 | 12.00 |
Claude 3 Opus | SASTSLLM | 9.83 | 2.31 | 3.00 | 12.00 |
ChatGPT4 | SASCPMLM | 7.99 | 1.95 | 5.00 | 10.00 |
Qwen 2.0 72B | SASCPMLM | 7.05 | 2.88 | 0 | 11.40 |
Claude 3 Opus | SASCPMLM | 5.64 | 2.28 | 2.00 | 12.00 |
Gemini Pro 1.5(0801) | SASCPMLM | 6.81 | 2.82 | 2.00 | 12..00 |