Semantic Tagging on UN Security Council resolutions
99.99Average Content Preservation Ratiogpt-4.1
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| gpt-4.1Input token cost=$2.00, Output token cost=$8.00, AVERAGE content size (characters)=5801.2, AVERAGE prompt tokens=1355.9, AVERAGE completion tokens=1824.252026.03 | 99.99 | 92.6 | 99.92 | 9.6 | 0.0173 | |
| gpt-5.1Input token cost=$1.25, Output token cost=$10.00, AVERAGE content size (characters)=5801.2, AVERAGE prompt tokens=1354.9, AVERAGE completion tokens=1834.552026.03 | 99.95 | 93.1 | 99.91 | 10.4 | 0.02 | |
| gpt-4.1-miniInput token cost=$0.40, Output token cost=$1.60, AVERAGE content size (characters)=5801.2, AVERAGE prompt tokens=1355.9, AVERAGE completion tokens=1744.82026.03 | 99.92 | 80.1 | 99.64 | 22.5 | 0.0033 | |
| gpt-4oInput token cost=$2.50, Output token cost=$10.00, AVERAGE content size (characters)=5801.2, AVERAGE prompt tokens=1355.9, AVERAGE completion tokens=1736.22026.03 | 97.1 | 86.25 | 99.91 | 9.7 | 0.0208 | |
| gpt-5-miniInput token cost=$0.25, Output token cost=$2.00, AVERAGE content size (characters)=5801.2, AVERAGE prompt tokens=1354.9, AVERAGE completion tokens=5623.852026.03 | 84.71 | 90.25 | 84.93 | 72.3 | 0.0116 | |
| gpt-4.1-nanoInput token cost=$0.10, Output token cost=$0.40, AVERAGE content size (characters)=5801.2, AVERAGE prompt tokens=1355.9, AVERAGE completion tokens=1222.952026.03 | 68.03 | 84.3 | 92.31 | 9.5 | 0.0006 | |
| gpt-5-nanoInput token cost=$0.05, Output token cost=$0.40, AVERAGE content size (characters)=5801.2, AVERAGE prompt tokens=1354.9, AVERAGE completion tokens=0.002026.03 | 0 | 0 | 0 | 36.4 | 0.0033 |