Solar Open 2 250B lands on Hugging Face with strong benchmark results
_akhaliq · x · 2026-07-22
- Solar Open 2 250B has reportedly dropped on Hugging Face.
- The accompanying chart compares it with Solar Open 100B and other open models across MMLU-Pro, MATH, LiveCodeBench, APEX-Agents, SWE-Bench Verified, and MCP-Atlas.
- The visible results show Solar Open 2 leading this comparison set on several benchmarks, including strong gains on reasoning, math, coding, and agentic tasks.
Related event: Upstage Releases Solar Open 2 250B Open-Weights Model(2 posts)→
More from Models
- MissionReport benchmark: only 3 of 540 AI-generated government reports pass all criteria — Exp_Mark · 2026-10-27
- Local beats cloud: Qwen 3.8 FN handles private student data as well as frontier models — dr_lm · 2026-10-27
- Aidan Gomez: model's CoT said no tool calls right before making them — aidangomez · 2026-10-27
- Nat Lambert: Cohere's model is narrow RL training on internal infra ill-suited for open weights — natolambert · 2026-10-27
- OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27