Command Palette
Search for a command to run...
Legal Reasoning On Legalbench Issue Spotting
Metriken
Balanced Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | Repository | ||
|---|---|---|---|
| GPT-4 | 82.9 | - | - |
| GPT-3.5 | 60.9 | - | - |
| Claude-1 | 58.1 | - | - |
0 of 3 row(s) selected.