Reasoning on MDM (test)
58.3AccuracyTCR-gold
Evaluation Results
| Method | Links | |
|---|---|---|
| TCR-goldBackbone=Qwen2.5-7B-Instruct, Intervention Method=TCR-gold2026.01 | 58.3 | |
| TCRBackbone=Qwen2.5-7B-Instruct, Intervention Method=TCR2026.01 | 48.2 | |
| TCR-goldBackbone=Qwen3-8B-Instruct, Intervention Method=TCR-gold2026.01 | 47.1 | |
| Qwen2.5-7B-InstructBackbone=Qwen2.5-7B-Instruct, Intervention Method=None2026.01 | 43 | |
| DoLaBackbone=Qwen2.5-7B-Instruct, Intervention Method=DoLa2026.01 | 38.5 | |
| TCRBackbone=Qwen3-8B-Instruct, Intervention Method=TCR2026.01 | 29.3 | |
| Qwen3-8B-InstructBackbone=Qwen3-8B-Instruct, Intervention Method=None2026.01 | 24.7 | |
| TCR-goldBackbone=Phi-3-Instruct, Intervention Method=TCR-gold2026.01 | 15.8 | |
| TCRBackbone=Phi-3-Instruct, Intervention Method=TCR2026.01 | 11.5 | |
| DoLaBackbone=Qwen3-8B-Instruct, Intervention Method=DoLa2026.01 | 9 | |
| Phi-3-InstructBackbone=Phi-3-Instruct, Intervention Method=None2026.01 | 8.1 | |
| DoLaBackbone=Phi-3-Instruct, Intervention Method=DoLa2026.01 | 6.7 | |
| LLaMA3-8B-InstructBackbone=LLaMA3-8B-Instruct, Intervention Method=None2026.01 | 0 | |
| DoLaBackbone=LLaMA3-8B-Instruct, Intervention Method=DoLa2026.01 | 0 | |
| TCRBackbone=LLaMA3-8B-Instruct, Intervention Method=TCR2026.01 | 0 | |
| TCR-goldBackbone=LLaMA3-8B-Instruct, Intervention Method=TCR-gold2026.01 | 0 |