ModelScope @ModelScope2022 · 02 Sep 2026
Agent capabilities in just 4B parameters, with native 1M context. Don’t miss Spark-X2.5-4B. Apache 2.0. 🤖 https://t.co/BT83fxmtLz 🏆 Beats Qwen3.5-9B on SWE-bench Pro (44.4 vs. 33.8) and SWE-bench Multilingual (53.3 vs. 43.3). 🛠️ Leads the comparison on τ³-bench, MCP-Atlas, https://t.co/WRRDjScOq7
25 894Views
492Likes
34Reposts
28Replies
10Quotes
313Bookmarks
Is that a lot?
1.70×vs this author's median15 192 views is typical
60Percentile for this authorof 5 recent posts
9.41×vs 10K–100K median2 751 views is typical
181.80%Reachviews ÷ followers
2.18%Engagement rateof viewers reacted