OpenBMB open-sources MiniCPM5-2B, top-ranked open model under 4B params
hey_abusiddik · x · 2026-09-08
OpenBMB (OpenBMB Lab) released MiniCPM5-2B, an open-source 2B-parameter edge language model focused on "intelligence density":
- Ranks #1 among open-source models under 4B on the Artificial Analysis Intelligence Index with a score of 23
- Scores 20 on the Agentic Index, offering early general-purpose agent capability on-device
- Averages 53.9 across 34 benchmarks covering coding, math, long context, tool use, and agentic tasks
The release also opens up the training data, recipes, and RL stack. A quote-tweet adds that smaller models don't just cut inference cost — they lower the cost of experimentation: more instances, more retries, more weird ideas builders can afford to test.
Related event: OpenBMB Open-Sources MiniCPM5-2B, Topping Sub-4B Open Models(14 posts)→
More from Models
- Open Models Match GPT-6 on MedMCQA but Trail 17 Points on Hard Clinical Cases — keunwoochoi · 2026-10-27
- Health-Focused Benchmark Reranks LLMs: Muse Spark Open Jumps from #9 to #1 — keunwoochoi · 2026-10-27
- DeepSeek cut KV cache per token from 389KB to 890B in two years as open-closed gap debate rages — teortaxesTex · 2026-10-27
- GPT-6 Astra controls dexterous hands zero-shot at just 5.2% success in 500 trials — stingning · 2026-10-27
- Unverified: fable 5.5 speculated at 4-5T parameters to outscale 1-3T Opus — haider1 · 2026-10-27
- Kimi K3 Is 'Open' Until You Succeed: License Caps Free Use at $20M Revenue — alex_verem · 2026-10-27