Reasoning on CLF (test)
99AccuracyTCR-gold
Evaluation Results
| Method | Links | |
|---|---|---|
| TCR-goldBackbone=Qwen3-8B-Instruct, Intervention Method=TCR-gold2026.01 | 99 | |
| TCRBackbone=Qwen3-8B-Instruct, Intervention Method=TCR2026.01 | 97 | |
| Qwen3-8B-InstructBackbone=Qwen3-8B-Instruct, Intervention Method=None2026.01 | 96.9 | |
| DoLaBackbone=Qwen3-8B-Instruct, Intervention Method=DoLa2026.01 | 94.4 | |
| TCR-goldBackbone=Qwen2.5-7B-Instruct, Intervention Method=TCR-gold2026.01 | 71.3 | |
| TCRBackbone=Qwen2.5-7B-Instruct, Intervention Method=TCR2026.01 | 66.6 | |
| Qwen2.5-7B-InstructBackbone=Qwen2.5-7B-Instruct, Intervention Method=None2026.01 | 56.8 | |
| DoLaBackbone=Qwen2.5-7B-Instruct, Intervention Method=DoLa2026.01 | 52.3 | |
| TCR-goldBackbone=LLaMA3-8B-Instruct, Intervention Method=TCR-gold2026.01 | 32.7 | |
| TCRBackbone=LLaMA3-8B-Instruct, Intervention Method=TCR2026.01 | 28.2 | |
| TCR-goldBackbone=Phi-3-Instruct, Intervention Method=TCR-gold2026.01 | 20.3 | |
| LLaMA3-8B-InstructBackbone=LLaMA3-8B-Instruct, Intervention Method=None2026.01 | 15.2 | |
| TCRBackbone=Phi-3-Instruct, Intervention Method=TCR2026.01 | 11.2 | |
| Phi-3-InstructBackbone=Phi-3-Instruct, Intervention Method=None2026.01 | 9.2 | |
| DoLaBackbone=LLaMA3-8B-Instruct, Intervention Method=DoLa2026.01 | 8.8 | |
| DoLaBackbone=Phi-3-Instruct, Intervention Method=DoLa2026.01 | 7.6 |