GaC(Qwen2-72B-Instruct + Llama-3-70B-Instruct)
Reported on 2 benchmarks across 2 tasks · 1 paper
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing1 result
- EM· 2024-06-1879.29best: 87.5 (Claude 2 (few-shot, k=5))
Reasoning1 result
- Accuracy· 2024-06-1890.91best: 97.72 (Claude 3.5 Sonnet (HPT))