Verified75% confidenceFactExact time
The o-series models score each intermediate reasoning step individually using a Process Reward Model, rather than relying solely on the correctness of the final result.
3
Sources
75%
Confidence
Long-term
Relevance
7/21/2026
First Seen
Sources
Related Claims
VerifiedA Process Reward Model (PRM) scores each intermediate step in a reasoning chain, as distinct from an Outcome Reward Model (ORM), which evaluates only the correctness of the final answer.80% similarUnverifiedIf rewards target only final outcomes, the model tends to take shortcuts and memorize solutions for specific scenarios.76% similarVerifiedThe o-series models combine chain-of-thought reasoning with reinforcement learning, with the model generating internal thinking steps before producing an answer.75% similarVerifiedReward model training can use learning-to-rank frameworks such as the Bradley-Terry model, training a neural network to predict the probability of human preference between any two responses, taking a (prompt, response) pair as input and outputting a scalar score.72% similarUnverified该研究使用「LLM作为裁判」的评估方式，只要本地模型胜出或与专有模型打平就计为一次胜利72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/582130API
curl https://kongchang.com/api/v1/knowledge/claims/582130MCP
get_claim(id=582130)