LMSYS Chatbot Arena (@arena) · 10/9/2026, 11:53:32
Mistral Large 4 Enters Top 15 in Agent Arena: 1T-Param Multimodal Preview Boosts Net Score by 6.6%
Mistral AI's newly released Mistral Large 4 (codenamed Le Chonk) achieved a -6.6% net improvement score across over 5,000 real-world agentic sessions in the Agent Arena, ranking 11 positions higher than its predecessor, Mistral Medium 3.5. The model features 1T total parameters with 49B active and native multimodality, currently available via API as a preview with open weights expected by late October.
SOURCE COVERAGEFull Original Report
Arena.ai (@arena) · 2026-10-09 03
Mistral Large 4 by @MistralAI has landed in the Agent Arena top 15 labs!
Across +5K real-world agentic sessions, this preview model records a -6.6% net improvement score. It is 11 rankings above the previous variant, Mistral Medium 3.5 (-12.60%).
Mistral Large 4 is #43 overall in the Agent Arena. Open weights are expected at the end of October, but at its current score Mistral Large 4 would rank #13 among open models.
@MistralAI is also the only European lab in the Agent Arena top 15. Congrats to the team!
↳ 引用 @MistralAI (Mistral AI): Meet Mistral Large 4, aka Le Chonk.
• 1T parameters, natively multimodal. 49B active. It is the best open weights model from US or Europe on aggregated benchmarks. • State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding. • Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure. • Available to all via API today. Working with cybersecurity partners privately.
Open weights release end of October.
156 赞 · 5 转发
