LLM Comparison

MiniCPM vs Trinity Large Preview

Side-by-side specs, pricing & capabilities · Updated September 2026

Add to comparison

2/6 models
Same tier:
 OpenBMBMiniCPMArcee AITrinity Large Preview
OrganizationOpenBMBOpenBMBArcee AIArcee AI
OpenTools Score
35
FamilyMiniCPMTrinity
StatusCurrentCurrent
Release DateJan 2026
Context Window128K tokens131K tokens
Input Price
Output Price
Pricing NotesOpen-weight GitHub and Hugging Face model family. There is no fixed vendor API price; runtime cost depends on the host, hardware, or inference provider.Free tier available on OpenRouter with rate limits
Capabilities
textcodereasoninglocal-inference
textcode
Training CutoffNot publicly specified in queued source
Max Output33K tokens
API IdentifierOpenBMB/MiniCPMarcee-ai/trinity-large-preview:free
Benchmarks
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
MMLU
87.2https://huggingface.co/arcee-ai/Trinity-Large-Preview
MMLU-Pro
75.2https://huggingface.co/arcee-ai/Trinity-Large-Preview
GPQA Diamond
63.3https://huggingface.co/arcee-ai/Trinity-Large-Preview
 View MiniCPMView Trinity Large Preview

Looking for more AI models?

Browse All LLMs