Unverified50% confidenceFactExact time
In mathematics reasoning research, OpenAI found that models trained with process supervision significantly outperform models trained with only outcome supervision on complex reasoning tasks.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOpenAI's research papers demonstrate that in domains such as mathematical reasoning, carefully designed synthetic data can surpass the training effectiveness of human-annotated data.79% similarUnverifiedOpenAI published research in 2023 showing that process reward models can significantly improve the reliability of mathematical reasoning compared to outcome supervision.79% similarUnverified辩论式提示研究由OpenAI等机构推进，让多个模型实例相互辩论并由裁判模型综合判断，在数学推理和事实核查任务上能超越单次生成的准确率78% similarUnverifiedReasoning models with the thinking function enabled perform significantly better than base models when handling counterintuitive questions.77% similarVerifiedResearch from OpenAI and Anthropic shows that using models matched to tasks of different complexity levels not only reduces inference costs but also improves overall output quality.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001200API
curl https://kongchang.com/api/v1/knowledge/claims/1001200MCP
get_claim(id=1001200)