# Perplexity Introduces JOLT Post-Training Method

JOLT matched GRPO accuracy on the MATH benchmark using 6.5x fewer training tokens.

- JOLT uses a single model as both teacher and student, supplying per-token feedback rather than a single reward per attempt.
- The teacher model receives extra context like verified solutions and is trained on outcome rewards with a penalty for diverging from student predictions.
- JOLT+ outperformed GRPO across five benchmarks covering math, coding, tool use, and terminal tasks, including a 9.9-point gain on AppWorld.

## Why it matters

Model developers can reduce post-training compute requirements while improving accuracy across multi-step reasoning and tool-use tasks.

## Sources

- [Perplexity: Perplexity Introduces JOLT Post-Training Method](https://x.com/perplexity_ai/status/2112978260808376411)

---

Summarized by dstilled on 2026-10-21. https://dstilled.ai/story/5e432f99-06a1-487d-a516-afe0d612cb56
