LLM Comparison
Maple-Preview vs MiniCPM
Side-by-side specs, pricing & capabilities · Updated September 2026
Add to comparison
2/6 models| Organization | ||
| OpenTools Score | 45 | |
| Family | Maple | MiniCPM |
| Status | Current | Current |
| Release Date | Aug 2026 | — |
| Context Window | 131K tokens | 128K tokens |
| Input Price | — | — |
| Output Price | — | — |
| Pricing Notes | Open-source model card; no hosted API pricing found in the official source. Local inference costs depend on user hardware and runtime. | Open-weight GitHub and Hugging Face model family. There is no fixed vendor API price; runtime cost depends on the host, hardware, or inference provider. |
| Capabilities | textreasoningcodeon-device-inference | textcodereasoninglocal-inference |
| Training Cutoff | — | Not publicly specified in queued source |
| Max Output | — | 33K tokens |
| API Identifier | deepgrove/maple-preview | OpenBMB/MiniCPM |
| Benchmarks | ||
| LiveCodeBench v6 | 75.1DeepGrove model card | — |
| AIME 2026 | 87.5DeepGrove model card | — |
| HMMT 2026 | 78.8DeepGrove model card | — |
| GPQA Diamond | 73.5DeepGrove model card | — |
| MiniCPM-SALA standard benchmark average | — | 76.53official-github-readme |
| MiniCPM-SALA long-context average | — | 38.97official-github-readme |
| MiniCPM-SALA 2048K extrapolation score | — | 81.6official-github-readme |
| MiniCPM4.1 reasoning decoding speedup | — | 3official-github-readme |
| MiniCPM4 Jetson AGX Orin decoding speedup vs Qwen3-8B | — | 7official-github-readme |
| View Maple-Preview | View MiniCPM | |
DeepGrove
Maple-Preview
Maple-Preview is DeepGrove’s open-source 20B-A1B ternary-weight reasoning LLM for efficient on-device inference. The model card reports 20.2B total parameters, 1.49B active parameters, a 131,072-token context window, and 5.31 GB checkpoint size. The model card specifies 131,072 tokens of context but does not establish a separate maximum output-token limit.
OpenBMB
MiniCPM
MiniCPM is OpenBMB’s ultra-efficient open language-model family for edge and end-device deployment. The MiniCPM4 and MiniCPM4.1 lines focus on fast local reasoning, while MiniCPM-SALA extends the family toward sparse/linear attention and million-token context research.
More Comparisons
Looking for more AI models?
Browse All LLMs