PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering

TL;DR

PRIME is a new benchmark designed to evaluate the ability of verifiers to check both the correctness of solutions and the correctness of their derivation processes in STEM problems, improving the reliability of reinforcement learning rewards.

Contribution

It introduces PRIME, a comprehensive benchmark for process-outcome alignment verification, and demonstrates its effectiveness in enhancing RLVR training for mathematical and engineering problems.

Findings

Current verifiers often miss derivation errors.

Process-aware RLVR training improves performance significantly.

Verifier accuracy on PRIME correlates strongly with RLVR training success.

Abstract

While model-based verifiers are essential for scaling Reinforcement Learning with Verifiable Rewards (RLVR), current outcome-centric verification paradigms primarily focus on the consistency between the final result and the ground truth, often neglecting potential errors in the derivation process. This leads to assigning positive rewards to correct answers produced from incorrect derivations. To bridge this gap, we introduce PRIME, a benchmark for evaluating verifiers on Process-Outcome Alignment verification in Mathematics and Engineering. Curated from a comprehensive collection of college-level STEM problems, PRIME comprises 2,530 high-difficulty samples through a consistency-based filtering pipeline. Through extensive evaluation, we find that current verifiers frequently fail to detect derivation flaws. Furthermore, we propose a process-aware RLVR training paradigm utilizing verifiers selected via PRIME. This approach substantially outperforms the outcome-only verification baseline, achieving absolute performance gains of 8.29%, 9.12%, and 7.31% on AIME24, AIME25, and Beyond-AIME, respectively, for the Qwen3-14B-Base model. Finally, we demonstrate a strong linear correlation ($R^2 > 0.92$) between verifier accuracy on PRIME and RLVR training effectiveness, validating PRIME as a reliable predictor for verifier selection.