This paper shows that Gemma 4 introduces a new generation of multimodal language models with 2.3B to 31B parameters, featuring improved compute efficiency and reasoning capabilities.
Gemma 4 introduces a new generation of multimodal language models with 2.3B to 31B parameters, featuring improved compute efficiency and reasoning capabilities. The model suite includes a unified architecture for the 12B model that processes raw audio and image patches, achieving significant performance gains across STEM and long-context benchmarks, rivaling larger models in human-rated tasks.
Authors:Gemma Team: Sherif El Abd, Vaibhav Aggarwal, Robin Algayres, Alek Andreev, Olivier Bachem, Ian Ballantyne, Cormac Brick, Victor Cărbune, Michelle Casbon, Mayank Chaturvedi, Victor Cotruta, Alice Coucke, Phil Culliton, Robert Dadashi, Lucas Dixon, Mohamed Elhawaty, Utku Evci, Clément Farabet, Johan Ferret, Filippo Galgani, Sertan Girgin, Jean-Bastien Grill, Maarten Grootendorst, Jiaxian Guo, Cassidy Hardin, Yanzhang He, Steven M. Hernandez, Omri Homburger, Léonard Hussenot, Juyeong Ji, Armand Joulin, Aishwarya Kamath, Parnian Kassraie, Olivier Lacombe, Preethi Lahoti, Gaël Liu, Gus Martins, Luciano Martins, Tatiana Matejovicova, Ramona Merhej, Nikola Momchev, Sneha Mondal, Ryan Mullins, Sindhu Raghuram Panyam, Shreya Pathak, Sarah Perrin, André Susano Pinto, Etienne Pot, Angéline Pouget, Alexandre Ramé, Sabela Ramos, Douglas Reid, David Rim, Morgane Rivière, Karsten Roth, Louis Rouillard, Omar Sanseviero, Pier Giuseppe Sessa, Shane Settle, Danila Sinopalnikov, Sara Smoot, Piotr Stanczyk, Andreas Steiner, Lawrence Stewart, Ilya Tolstikhin, Michael Tschannen, Anton Tsitsulin, Nino Vieillard, Renjie Wu, Pingmei Xu, Haichuan Yang, Edouard Yvinec, Li Zhang, Joe Zou, Nicolas Aagnes, Abdelrahman Abdelhamed, Shivani Agrawal, Shubham Agrawal, Ibrahim Alabdulmohsin, Jean Baptiste Alayrac, Uri Alon, Chandramouli Amarnath, Ankesh Anand, Chrysovalantis Anastasiou, Setareh Ariafar, François-Xavier Aubet, Kyriakos Axiotis, Federico Barbero, Joelle Barral, Alexei Bendebury, Urs Bergmann, Stanley Bileschi, Kat Black, Mathieu Blondel, Sebastian Borgeaud, Arthur Bražinskas, Ryan Burnell, Robert Busa-Fekete, Mu Cai
et al. (201 additional authors not shown)
Abstract:We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemma 4 model suite features dense and Mixture-of-Experts architectures, ranging from 2.3B to 31B parameters. Alongside improved vision and audio encoders for all model sizes, we propose a unified, encoder-free architecture for our 12B model, which ingests raw audio and image patches. Furthermore, we integrate a thinking mode, enabling Gemma models to generate reasoning traces prior to responding. We improve inference speed, memory, and compute efficiency, as well as long-context abilities through critical design choices. Gemma 4 establishes a leap in performance across STEM, multimodal, and long-context benchmarks, and rivals larger, frontier open models in human-rated tasks.
| Comments: | 17 pages, 2 figures, technical report |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.02770 [cs.CL] |
| (or arXiv:2607.02770v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.02770 arXiv-issued DOI via DataCite (pending registration) |
From: Johan Ferret [view email]
[v1]
Thu, 2 Jul 2026 21:08:53 UTC (330 KB)
— Originally published at arxiv.org
Daily brief at your local 8am — bilingual EN/中文, free.
The study introduces the Normalized Context Utilization (NCU) metric to evaluate Retrieval-Augmented Generation (RAG) systems, revealing that Small Language Models (SLMs) outperform larger models in factual extraction. The findings indicate that traditional scaling laws yield diminishing returns, with a commercial API frequently failing against adversarial evidence due to systemic confidence collapse.
The REFLECT benchmark reveals that current LLM judges are unreliable, achieving below 55% accuracy in evaluating reasoning and evidence use, highlighting the need for improved evaluation methods for deep research agents.
This study evaluates LLM-based urban simulators like AgentSociety and CitySim, revealing a significant gap between narrative plausibility and real-world mobility realism. Using datasets from Greater Paris and Shanghai, the analysis shows these models struggle with core spatial and temporal constraints, necessitating rigorous empirical validation and improved initialization methods for realistic urban simulations.