Agent on BFCL AST NON LIVE
87.36AccuracyDeepSeek-R1
Evaluation results
| Method | Links | |
|---|---|---|
| DeepSeek-R12025.12 | 87.36 | |
| CompassMax-V32025.12 | 86.46 | |
| CompassMax-V3-Thinking2025.12 | 83.73 |
| Method | Links | |
|---|---|---|
| DeepSeek-R12025.12 | 87.36 | |
| CompassMax-V32025.12 | 86.46 | |
| CompassMax-V3-Thinking2025.12 | 83.73 |