PaLM 540B maj1@40 (8-shot)

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Reasoning2 results

Arithmetic ReasoningonGSM8K
Accuracy· uses extra data· 2022-03-21
74.4
best: 97.72 (Claude 3.5 Sonnet (HPT))
SOTA
Self-Consistency Improves Chain of Thought Reasoning in Language Models arXiv:2203.11171
Arithmetic ReasoningonGSM8K
Parameters (Billion)· uses extra data· 2022-03-21
540
SOTA
Self-Consistency Improves Chain of Thought Reasoning in Language Models arXiv:2203.11171