MiniCPM5-2B: Intelligence, Performance & Price Analysis
Model summary
Performance
Verbosity
MiniCPM5-2B supports text input, outputs text, and has a 131k tokens context window with knowledge up to December 2025.
| Reasoning | Yes |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text |
| Knowledge cutoff | Dec 31, 2025 |
| Context window | 131k ~197 A4 pages of size 12 Arial font |
| Total parameters | 2.6B |
| License | Apache 2.0 |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Time per Task
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Evaluations
Agentic knowledge work, Elo
Agentic SaaS workflows
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Agentic real-world work tasks, Elo
Openness Index
Artificial Analysis Openness Index: Score
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Context Window
Context Window
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Further details
Weights | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| MiniCPM5-2B | - | 2.6B | 131k | - | - | - | - |
More from OpenBMB
Frequently Asked Questions
Common questions about MiniCPM5-2B
MiniCPM5-2B was released on September 7, 2026.
MiniCPM5-2B was created by OpenBMB.
Yes, MiniCPM5-2B is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
MiniCPM5-2B supports text input.
MiniCPM5-2B supports text output.
No, MiniCPM5-2B does not support image input. It can only process text.
No, MiniCPM5-2B is not multimodal. It only supports text input.
MiniCPM5-2B has a context window of 131k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, MiniCPM5-2B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
MiniCPM5-2B has 2.6B parameters.
MiniCPM5-2B is released under the Apache 2.0 license. This license allows commercial use. View license
MiniCPM5-2B has a knowledge cutoff of December 2025. The model's training data includes information up to this date.
MiniCPM5-2B is an open weights model that can be self-hosted. View providers
MiniCPM5-2B is an open weights model that can be downloaded and self-hosted. Compare providers