Binary Classification on German Credit (Accuracy)
68.9AccuracyIDEA
Evaluation Results
| Method | Links | |
|---|---|---|
| IDEAModel=Qwen-3-32B2026.04 | 68.9 | |
| CoTModel=GPT-5.22026.04 | 68.2 | |
| IDEA w/o EMModel=Qwen-3-32B2026.04 | 63.2 | |
| VanillaModel=Qwen-3-32B2026.04 | 63 | |
| LogitModel=Qwen-3-32B2026.04 | 61.1 | |
| IDEA w/o InterModel=Qwen-3-32B2026.04 | 60.6 | |
| IDEAModel=Qwen-3-8B2026.04 | 60.3 | |
| IDEA w/o EMModel=Qwen-3-8B2026.04 | 60.2 | |
| BIRDModel=Qwen-3-32B2026.04 | 59.2 | |
| IDEA w/o InterModel=Qwen-3-8B2026.04 | 58.9 | |
| IDEA w/o MCModel=Qwen-3-8B2026.04 | 58.9 | |
| VanillaModel=Qwen-3-8B2026.04 | 58.6 | |
| CoTModel=Qwen-3-8B2026.04 | 58.5 | |
| LogitModel=Qwen-3-8B2026.04 | 58.5 | |
| IDEA w/o MCModel=Qwen-3-32B2026.04 | 58.1 | |
| CoTModel=Qwen-3-4B2026.04 | 57.5 | |
| CoTModel=DeepSeek R12026.04 | 57 | |
| VanillaModel=Qwen-3-4B2026.04 | 56.1 | |
| CoTModel=Qwen-3-32B2026.04 | 56 | |
| BIRDModel=Qwen-3-8B2026.04 | 55.1 | |
| LogitModel=Qwen-3-4B2026.04 | 54.9 | |
| IDEA w/o MCModel=Qwen-3-4B2026.04 | 53.5 | |
| IDEA w/o InterModel=Qwen-3-4B2026.04 | 53.4 | |
| IDEAModel=Qwen-3-4B2026.04 | 53.3 | |
| BIRDModel=Qwen-3-4B2026.04 | 53.1 | |
| IDEA w/o EMModel=Qwen-3-4B2026.04 | 52.7 | |
| RandomModel=N/A2026.04 | 50 |