OVM-Mistral-7B (verify20@1)

Reported on 2 benchmarks across 1 task · 1 paper

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

Reasoning2 results

Arithmetic ReasoningonGSM8K
Accuracy· 2023-11-16
82.6
best: 97.72 (Claude 3.5 Sonnet (HPT))
OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning arXiv:2311.09724
Arithmetic ReasoningonGSM8K
Parameters (Billion)· 2023-11-16
7
best: 540 (PaLM 540B (Self Improvement, Self Consistency))
OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning arXiv:2311.09724