RESEARCH
CORE MACHINE LEARNING
Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
November 18, 2025
Abstract
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, but their training remains resource- and time-intensive, requiring massive compute power and careful orchestration of training procedures. Model souping—the practice of averaging weights from multiple models of the same architecture—has emerged as a promising pre- and post-training technique that can enhance performance without expensive retraining. In this paper, we introduce Soup Of Category Experts (SoCE), a principled approach for model souping that utilizes benchmark composition to identify optimal model candidates and applies non-uniform weighted averaging to maximize performance. Contrary to previous uniform-averaging approaches, our method leverages the observation that benchmark categories often exhibit low inter-correlations in model performance. SoCE identifies "expert" models for each weakly-correlated category cluster and combines them using optimized weighted averaging rather than uniform weights. We demonstrate that the proposed method improves performance and robustness across multiple domains, including multilingual capabilities, tool calling, and math and achieves state-of-the-art results on the Berkeley Function Calling Leaderboard.
AUTHORS
Written by
Shalini Maiti *
Amar Budhiraja *
Bhavul Gauri
Gaurav Chaurasia
Anton Protopopov
Alexis Audran-Reiss
Michael Slater
Despoina Magka
Tatiana Shavrina
Roberta Raileanu
Yoram Bachrach
* Equal authorship
Publisher
arXiv
Research Topics
Related Publications
May 06, 2026
HUMAN & MACHINE INTELLIGENCE
RESEARCH
NeuralBench: A Unifying Framework to Benchmark NeuroAI Models
Hubert Banville, Stéphane d'Ascoli, Simon Dahan, Jérémy Rapin, Marlene Careil, Yohann Benchetrit, Jarod Levy, Saarang Panchavati, Antoine Ratouchniak, Mingfang (Lucy) Zhang, Elisa Cascardi, Katelyn Begany, Teon Brooks, Jean-Rémi King
May 06, 2026
April 16, 2026
RESEARCH
AIRA₂: Overcoming Bottlenecks in AI Research Agents
Karen Hambardzumyan, Nicolas Baldwin, Edan Toledo, Rishi Hazra, Michael Kuchnik, Bassel Al Omari, Thomas Simon Foster, Anton Protopopov, Jean-Christophe Gagnon-Audet, Ishita Mediratta, Kelvin Niu, Michael Shvartsman, Alisia Lupidi, Alexis Audran-Reiss, Parth Pathak, Tatiana Shavrina, Despoina Magka, Hela Momand, Derek Dunfield, Nicola Cancedda, Pontus Stenetorp, Carole-Jean Wu, Jakob Foerster, Yoram Bachrach, Martin Josifoski
April 16, 2026
March 17, 2026
RESEARCH
NLP
Omnilingual MT: Machine Translation for 1,600 Languages
Omnilingual MT Team, Belen Alastruey, Niyati Bafna, Andrea Caciolai, Kevin Heffernan, Artyom Kozhevnikov, Christophe Ropers, Eduardo Sánchez, Charles-Eric Saint-James, Ioannis Tsiamas, Chierh CHENG, Joe Chuang, Paul-Ambroise Duquenne, Mark Duppenthaler, Nate Ekberg, Cynthia Gao, Pere Lluís Huguet Cabot, João Maria Janeiro, Jean Maillard, Gabriel Mejia Gonzalez, Holger Schwenk, Edan Toledo, Arina Turkatenko, Albert Ventayol-Boada, Rashel Moritz, Alexandre Mourachko, Surya Parimi, Mary Williamson, Shireen Yates, David Dale, Marta R. Costa-jussa
March 17, 2026
March 17, 2026
RESEARCH
SPEECH & AUDIO
Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech
Omnilingual SONAR Team, João Maria Janeiro, Pere Lluís Huguet Cabot, Ioannis Tsiamas, Yen Meng, Vivek Iyer, Guillem Ramirez, Loic Barrault, Belen Alastruey, Yu-An Chung, Marta R. Costa-jussa, David Dale, Kevin Heffernan, Jaehyeong Jo, Artyom Kozhevnikov, Alexandre Mourachko, Christophe Ropers, Holger Schwenk, Paul-Ambroise Duquenne
March 17, 2026
Help Us Pioneer The Future of AI
We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.
Our approach
Latest news
Foundational models
Meta © 2026