PaLM 2 (few-shot, k=4, CoT)
Reported on 4 benchmarks across 4 tasks · 1 paper
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Knowledge Base2 results
- Accuracy· 2023-05-1734.3best: 89.7 (Gemini 2.0 Flash Experimental)
- Accuracy· 2023-05-1734.3best: 89.7 (Gemini 2.0 Flash Experimental)
Natural Language Processing1 result
- Accuracy· 2023-05-1734.3best: 89.7 (Gemini 2.0 Flash Experimental)
Reasoning1 result
- Accuracy· 2023-05-1734.3best: 89.7 (Gemini 2.0 Flash Experimental)