Code Execution on Qwen-Agent Code Interpreter Average
70.5AccuracyMatPlotAgent
Evaluation Results
| Method | Links | |
|---|---|---|
| MatPlotAgentVisual Feedback=Enabled2024.02 | 70.5 | |
| MatPlotAgentVisual Feedback=Disabled2024.02 | 66.3 | |
| GPT-42024.02 | 63.8 |
| Method | Links | |
|---|---|---|
| MatPlotAgentVisual Feedback=Enabled2024.02 | 70.5 | |
| MatPlotAgentVisual Feedback=Disabled2024.02 | 66.3 | |
| GPT-42024.02 | 63.8 |