Binary decision on BIGDATA 22
69.3AccuracyIDEA
Evaluation Results
| Method | Links | |
|---|---|---|
| IDEAModel=Qwen-3-32B2026.04 | 69.3 | |
| CoTModel=GPT-5.22026.04 | 67.8 | |
| IDEAModel=Qwen-3-8B2026.04 | 59.5 | |
| VanillaModel=Qwen-3-8B2026.04 | 59.1 | |
| VanillaModel=Qwen-3-32B2026.04 | 58.8 | |
| IDEAModel=Qwen-3-4B2026.04 | 56.8 | |
| VanillaModel=Qwen-3-4B2026.04 | 56.7 | |
| BIRDModel=Qwen-3-8B2026.04 | 56.2 | |
| LogitModel=Qwen-3-8B2026.04 | 56.1 | |
| LogitModel=Qwen-3-32B2026.04 | 55.7 | |
| BIRDModel=Qwen-3-32B2026.04 | 55.3 | |
| IDEA w/o MCModel=Qwen-3-32B2026.04 | 55.3 | |
| IDEA w/o EMModel=Qwen-3-4B2026.04 | 55.2 | |
| BIRDModel=Qwen-3-4B2026.04 | 55.1 | |
| IDEA w/o InterModel=Qwen-3-4B2026.04 | 54.4 | |
| IDEA w/o MCModel=Qwen-3-4B2026.04 | 54.3 | |
| IDEA w/o EMModel=Qwen-3-8B2026.04 | 52.8 | |
| IDEA w/o MCModel=Qwen-3-8B2026.04 | 52.5 | |
| LogitModel=Qwen-3-4B2026.04 | 52.4 | |
| CoTModel=DeepSeek R12026.04 | 51.8 | |
| IDEA w/o InterModel=Qwen-3-32B2026.04 | 51.7 | |
| IDEA w/o EMModel=Qwen-3-32B2026.04 | 51.6 | |
| CoTModel=Qwen-3-4B2026.04 | 51.4 | |
| CoTModel=Qwen-3-32B2026.04 | 51.4 | |
| IDEA w/o InterModel=Qwen-3-8B2026.04 | 50.8 | |
| CoTModel=Qwen-3-8B2026.04 | 50.7 | |
| RandomModel=N/A2026.04 | 50 |