‹ back to 2026-07-23

Solar Open 2 Technical Report

arXiv cs.CL LLM Agents Sungrae Park, Sanghoon Kim, Gyoungjin Gim, Jungho Cho, Hyunwoong Ko, Minbyul Jeong, Minjeong Kim, Keunwoo Choi, Chaehun Shin, Chanwoong Yoon, Dongjun Kim, Eunwon Kim, Gyungin Shin, Hyeonju Lee, Hyungkyu Kang, Inseo Song, Jisu Bae, Jiyoon Han, Jiyun Lee, Joonkee Kim, Junyeop Lee, Mikyoung Cha, Sangwon Yu, Sehwan Joo, Seokyoon Kang, Seonghoon Yang, Seung Shin, Seunghyun Lee, Seungseop Lim, Seungyoun Shin, Sukyung Lee, Taegyeong Eo, Taehwan Oh, Taewhoo Lee, Wonho Song, Wonjun Oh, Wonseok Hwang, Yunsu Kim, Yura Shim, Hwalsuk Lee, Sunghun Kim, Du-Seong Chang, Kyunghyun Cho, Seungju Han, Yejin Choi, Junsuk Choe, Hwaran Lee, Minjeong Ban, Yun Taewon, Hwanjun Song, Jae-Gil Lee, KyungTae Lim, Alice Oh 2026-07-22

TL;DR - Solar Open 2 is a 250B-parameter Mixture-of-Experts model with 15B active parameters, designed for long-horizon agentic tasks. It combines a 1M-token context window, compute-efficient pretraining, and multi-teacher distillation to achieve strong English and Korean benchmark results.

Uses hybrid linear and softmax attention without positional encoding to support 1M-token contexts.
Reuses Solar Open 1’s 5.69B-parameter shared skeleton and trains on a value-curated 10T-token mixture drawn from a 20T-token pool.
Consolidates 12 domain specialists through Multi-teacher On-Policy Distillation.
Leads comparably sized open-weight models on MMLU-Pro, LiveCodeBench, and APEX-Agents, while posting the highest reported Korean benchmark average among compared models.

view merged work →