Coding on Coding Real-data 20% verified
63.92Original AccuracyLogistic Regression
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Logistic RegressionModel=GPT-5.4, Data=29492026.06 | 63.92 | 59.54 | -4.38 | 590 | |
| Multilayer PerceptronModel=GPT-5.4, Data=29492026.06 | 63.92 | 60.83 | -3.09 | 590 | |
| Random ForestModel=GPT-5.4, Data=29492026.06 | 63.92 | 63.23 | -0.69 | 590 | |
| Label PropagationModel=GPT-5.4, Data=29492026.06 | 63.92 | 60.5 | -3.42 | 590 | |
| nnPUModel=GPT-5.4, Data=29492026.06 | 63.92 | 63.86 | -0.06 | 590 | |
| AURAModel=GPT-5.4, Data=29492026.06 | 63.92 | 67.2 | 3.28 | 100.6 | |
| Logistic RegressionModel=Gemini, Data=28202026.06 | 63.55 | 59.72 | -3.83 | 564 | |
| Multilayer PerceptronModel=Gemini, Data=28202026.06 | 63.55 | 61.76 | -1.79 | 564 | |
| Random ForestModel=Gemini, Data=28202026.06 | 63.55 | 63.39 | -0.16 | 564 | |
| Label PropagationModel=Gemini, Data=28202026.06 | 63.55 | 58.65 | -4.89 | 564 | |
| nnPUModel=Gemini, Data=28202026.06 | 63.55 | 63.51 | -0.04 | 564 | |
| AURAModel=Gemini, Data=28202026.06 | 63.55 | 67.17 | 3.62 | 96.6 | |
| Logistic RegressionModel=GPT-5.4-mini, Data=29712026.06 | 63.24 | 59.2 | -4.04 | 594 | |
| Multilayer PerceptronModel=GPT-5.4-mini, Data=29712026.06 | 63.24 | 61.4 | -1.85 | 594 | |
| Random ForestModel=GPT-5.4-mini, Data=29712026.06 | 63.24 | 63.27 | 0.03 | 594 | |
| Label PropagationModel=GPT-5.4-mini, Data=29712026.06 | 63.24 | 54.38 | -8.87 | 594 | |
| nnPUModel=GPT-5.4-mini, Data=29712026.06 | 63.24 | 63.43 | 0.19 | 594 | |
| AURAModel=GPT-5.4-mini, Data=29712026.06 | 63.24 | 66.27 | 3.03 | 102.2 | |
| Logistic RegressionModel=Qwen, Data=88842026.06 | 53.73 | 58.47 | 4.75 | 1,777 | |
| Multilayer PerceptronModel=Qwen, Data=88842026.06 | 53.73 | 57.44 | 3.72 | 1,777 | |
| Random ForestModel=Qwen, Data=88842026.06 | 53.73 | 59.2 | 5.47 | 1,777 | |
| Label PropagationModel=Qwen, Data=88842026.06 | 53.73 | 53.77 | 0.04 | 1,777 | |
| nnPUModel=Qwen, Data=88842026.06 | 53.73 | 58.54 | 4.81 | 1,777 | |
| AURAModel=Qwen, Data=88842026.06 | 53.73 | 77.74 | 24.02 | 278.8 | |
| Logistic RegressionModel=Mistral, Data=82402026.06 | 50.29 | 57.52 | 7.22 | 1,648 | |
| Multilayer PerceptronModel=Mistral, Data=82402026.06 | 50.29 | 56.82 | 6.53 | 1,648 | |
| Random ForestModel=Mistral, Data=82402026.06 | 50.29 | 58.88 | 8.59 | 1,648 | |
| Label PropagationModel=Mistral, Data=82402026.06 | 50.29 | 53.83 | 3.53 | 1,648 | |
| nnPUModel=Mistral, Data=82402026.06 | 50.29 | 57.97 | 7.68 | 1,648 | |
| AURAModel=Mistral, Data=82402026.06 | 50.29 | 72.91 | 22.62 | 261.8 |