Reasoning on MOAS (test)
95.8AccuracyTCR-gold
Evaluation Results
| Method | Links | |
|---|---|---|
| TCR-goldBackbone=Qwen3-8B-Instruct, Intervention Method=TCR-gold2026.01 | 95.8 | |
| TCRBackbone=Qwen3-8B-Instruct, Intervention Method=TCR2026.01 | 93.6 | |
| Qwen3-8B-InstructBackbone=Qwen3-8B-Instruct, Intervention Method=None2026.01 | 92.7 | |
| DoLaBackbone=Qwen3-8B-Instruct, Intervention Method=DoLa2026.01 | 89.7 | |
| TCR-goldBackbone=Qwen2.5-7B-Instruct, Intervention Method=TCR-gold2026.01 | 62 | |
| TCR-goldBackbone=LLaMA3-8B-Instruct, Intervention Method=TCR-gold2026.01 | 47 | |
| TCRBackbone=Qwen2.5-7B-Instruct, Intervention Method=TCR2026.01 | 46 | |
| DoLaBackbone=Qwen2.5-7B-Instruct, Intervention Method=DoLa2026.01 | 40 | |
| TCRBackbone=LLaMA3-8B-Instruct, Intervention Method=TCR2026.01 | 39.4 | |
| Qwen2.5-7B-InstructBackbone=Qwen2.5-7B-Instruct, Intervention Method=None2026.01 | 39.2 | |
| DoLaBackbone=LLaMA3-8B-Instruct, Intervention Method=DoLa2026.01 | 29.8 | |
| LLaMA3-8B-InstructBackbone=LLaMA3-8B-Instruct, Intervention Method=None2026.01 | 22.9 | |
| TCRBackbone=Phi-3-Instruct, Intervention Method=TCR2026.01 | 4 | |
| TCR-goldBackbone=Phi-3-Instruct, Intervention Method=TCR-gold2026.01 | 4 | |
| Phi-3-InstructBackbone=Phi-3-Instruct, Intervention Method=None2026.01 | 1 | |
| DoLaBackbone=Phi-3-Instruct, Intervention Method=DoLa2026.01 | 1 |