Reasoning on ObjC (test)
90AccuracyTCR-gold
Evaluation Results
| Method | Links | |
|---|---|---|
| TCR-goldBackbone=Qwen3-8B-Instruct, Intervention Method=TCR-gold2026.01 | 90 | |
| TCRBackbone=Qwen3-8B-Instruct, Intervention Method=TCR2026.01 | 88.1 | |
| Qwen3-8B-InstructBackbone=Qwen3-8B-Instruct, Intervention Method=None2026.01 | 85 | |
| DoLaBackbone=Qwen3-8B-Instruct, Intervention Method=DoLa2026.01 | 82.7 | |
| TCR-goldBackbone=LLaMA3-8B-Instruct, Intervention Method=TCR-gold2026.01 | 76.4 | |
| TCR-goldBackbone=Qwen2.5-7B-Instruct, Intervention Method=TCR-gold2026.01 | 76 | |
| DoLaBackbone=LLaMA3-8B-Instruct, Intervention Method=DoLa2026.01 | 71.2 | |
| LLaMA3-8B-InstructBackbone=LLaMA3-8B-Instruct, Intervention Method=None2026.01 | 68.8 | |
| TCRBackbone=LLaMA3-8B-Instruct, Intervention Method=TCR2026.01 | 67.8 | |
| TCRBackbone=Qwen2.5-7B-Instruct, Intervention Method=TCR2026.01 | 56 | |
| DoLaBackbone=Qwen2.5-7B-Instruct, Intervention Method=DoLa2026.01 | 52.3 | |
| Qwen2.5-7B-InstructBackbone=Qwen2.5-7B-Instruct, Intervention Method=None2026.01 | 52 | |
| TCRBackbone=Phi-3-Instruct, Intervention Method=TCR2026.01 | 45 | |
| TCR-goldBackbone=Phi-3-Instruct, Intervention Method=TCR-gold2026.01 | 45 | |
| Phi-3-InstructBackbone=Phi-3-Instruct, Intervention Method=None2026.01 | 30.9 | |
| DoLaBackbone=Phi-3-Instruct, Intervention Method=DoLa2026.01 | 29 |