Deterministic Inference Evaluation on AMC'23
0Avg Max Probability DivergenceBIO+TBIK
Evaluation Results
| Method | Links | |
|---|---|---|
| BIO+TBIKModel=Qwen3-8B2025.11 | 0 | |
| BIO+TBIKModel=Mistral-7B-Instruct2025.11 | 0 | |
| BIO+TBIKModel=Llama-3.1-8B-Instruct2025.11 | 0 | |
| BIO+TBIKModel=Qwen3-32B2025.11 | 0 | |
| BF16Model=Qwen3-8B2025.11 | 6.79 | |
| BIOModel=Qwen3-8B2025.11 | 6.9 | |
| BIOModel=Qwen3-32B2025.11 | 8.97 | |
| BF16Model=Qwen3-32B2025.11 | 9.8 | |
| BIOModel=Mistral-7B-Instruct2025.11 | 15.87 | |
| BF16Model=Mistral-7B-Instruct2025.11 | 19.88 | |
| BIOModel=Llama-3.1-8B-Instruct2025.11 | 21.06 | |
| BF16Model=Llama-3.1-8B-Instruct2025.11 | 31.09 |