# Li Auto's 35B Mach-Mind-4-Flash Reports Matching 120B-Class Models on Math and Code

The mixture-of-experts model activates just 3 billion parameters and claims 92.7 on AIME 2026 and 80.9 on LiveCodeBench, gains it credits entirely to post-training.

- Published: 2026-07-19T05:30:22.062Z
- Canonical: https://polylog.news/ai/2026-07-19/li-auto-s-35b-mach-mind-4-flash-reports-matching-120b-class
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [arXiv](https://arxiv.org/abs/2607.09375)

The AI division of Chinese electric-vehicle maker Li Auto published a technical report on Mach-Mind-4-Flash, a mixture-of-experts model with 35 billion total parameters and only 3 billion active at inference. As flagged in Russian-language…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-07-19/li-auto-s-35b-mach-mind-4-flash-reports-matching-120b-class (subscription information: https://polylog.news/pricing).