Solar Open 2 tops Korean benchmarks with an 85.4 average score
keunwoochoi · x · 2026-07-26
- The post says Solar Open 2 performs very well on Korean tasks and points to appendix examples from regulatory documents.
- The attached benchmark screenshot shows Solar Open 2 posting the highest average across six models on the Korean suite, at 85.4, ahead of DeepSeek-V4-Flash, GPT-5.4 mini, and Claude Haiku 4.5.
- It also appears near the top on several Korean-language and professional-domain benchmarks such as CLICK, KBank-MMLU, KBL, and KMMU-Pro.
Related event: Upstage Releases Solar Open 2: A 250B Sovereign LLM(6 posts)→
More from Models
- Fork builds engine to run Qwen at ~400 tok/s on three used V100s — jfinkpottery · 2026-10-27
- Meta joins frontier labs reporting CoT controllability evals in Muse Spark 1.3 card — tomekkorbak · 2026-10-27
- The tokenizer tax: AI models cost more when you don't use English — postalex · 2026-10-27
- Meta's Muse Spark 1.3 System Card Relies on Four Tübingen Benchmarks — maksym_andr · 2026-10-27
- ChatGPT Pro 500 Spotted: £445/Month Tier With Shared Weekly Usage Limits — yoimnotkesku · 2026-10-27
- Experts Clash: Today's Models Dwarf GPT-4, But Journal Delays Lock Out New LLMs — DeryaTR_ · 2026-10-27