Command Palette
Search for a command to run...
Legal Reasoning On Legalbench Issue Spotting
Metrics
Balanced Accuracy
Results
Performance results of various models on this benchmark
| Paper Title | Repository | ||
|---|---|---|---|
| GPT-4 | 82.9 | - | - |
| GPT-3.5 | 60.9 | - | - |
| Claude-1 | 58.1 | - | - |
0 of 3 row(s) selected.