OpenBMB Releases MiniCPM5-2B: A 2.52B Dense Model Averaging 53.9 Across 34 Benchmarks and Built to Run On Device
This story is from 2026-09-07. It is preserved in the archive; the latest stories are on the live feed.
OpenBMB has released MiniCPM5-2B, a dense causal language model with 2,516,756,480 parameters and a native 131,072 token context. It averages 53.9 across the 34 benchmarks in its model card, ahead of Qwen3.5-4B at 51.1, with its clearest leads in tool use, coding agents and long-context retrieval.…
Read the full story at MarkTechPost ↗
Timeline · 1 report
- 2026-09-07 19:18 · MarkTechPost
OpenBMB Releases MiniCPM5-2B: A 2.52B Dense Model Averaging 53.9 Across 34 Benchmarks and Built to Run On Device