Binary Classification on 42 analyzed code functions
93Macro F1gpt-4.1
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| gpt-4.1Prompt Strategy=P22026.03 | 93 | 0.0368 | |
| gpt-4.1Prompt Strategy=P12026.03 | 89.32 | — | |
| gpt-4.1-miniPrompt Strategy=P42026.03 | 83.97 | 0.0317 | |
| gpt-4.1-miniPrompt Strategy=P12026.03 | 80.8 | — | |
| gemini-2.5-flashPrompt Strategy=P42026.03 | 77.44 | 0.0009 | |
| gemini-2.5-flashPrompt Strategy=P12026.03 | 77.32 | — | |
| gpt-4o-miniPrompt Strategy=P42026.03 | 73.8 | 0.1288 | |
| gpt-4o-miniPrompt Strategy=P12026.03 | 60.92 | — | |
| gpt-3.5-turboPrompt Strategy=P42026.03 | 54.51 | 0.0238 | |
| gpt-3.5-turboPrompt Strategy=P12026.03 | 52.13 | — |