MiniCPM-V 4.6 1.3B
Intelligence
12.7
#386/520
Coding
0.7
#421/426
Math
—
Speed
—
Pricing
—
MiniCPM-V 4.6 1.3B is OpenBMB’s model designed for various natural language processing tasks. It features an Intelligence Index of 12.7, indicating its capability in understanding and generating text, while being priced at $0 per million tokens, making it accessible for users.
When to Use MiniCPM-V 4.6 1.3B
✓ Best For
- Text generation and completion tasks.
- Basic coding assistance.
- Simple mathematical problem solving.
✗ Not Ideal For
- High-speed processing needs due to 0 tok/sec speed.
- Complex mathematical computations where Math Index is not available.
How MiniCPM-V 4.6 1.3B Compares
Intelligence Index · Higher is better
OpenAIAlibabaOpenBMBGoogleMistral
Benchmark Profile
Coding Index
Liquid AIOpenBMBMetaIBM
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (8)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 12.7 | |
| Coding Index | 0.7 | |
| GPQA | 305% | |
| HLE | 49% | |
| SciCode | 2.1% | |
| IFBench | 26.7% | |
| LCR | 6.3% | |
| Tau2 | 87.7% |
Data: Artificial Analysis · Updated: May 11, 2026
Frequently Asked Questions (15)
When was MiniCPM-V 4.6 1.3B released?
MiniCPM-V 4.6 1.3B was released on May 11, 2026.
Who created MiniCPM-V 4.6 1.3B?
MiniCPM-V 4.6 1.3B was created by OpenBMB.
How intelligent is MiniCPM-V 4.6 1.3B?
MiniCPM-V 4.6 1.3B scores 13 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 8).
How verbose is MiniCPM-V 4.6 1.3B?
When evaluated on the Intelligence Index, MiniCPM-V 4.6 1.3B generated 5.4M output tokens, which is better than average compared to other open weight non-reasoning models of similar size (median: 5.4M).
Is MiniCPM-V 4.6 1.3B a reasoning model?
No, MiniCPM-V 4.6 1.3B is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does MiniCPM-V 4.6 1.3B support?
MiniCPM-V 4.6 1.3B supports text, image, and video input.
What output modalities does MiniCPM-V 4.6 1.3B support?
MiniCPM-V 4.6 1.3B supports text output.
Can MiniCPM-V 4.6 1.3B process images?
Yes, MiniCPM-V 4.6 1.3B supports image input and can analyze, describe, and answer questions about images.
Is MiniCPM-V 4.6 1.3B multimodal?
Yes, MiniCPM-V 4.6 1.3B is multimodal. It can process text, image, and video input and generate text output.
What is the context window of MiniCPM-V 4.6 1.3B?
MiniCPM-V 4.6 1.3B has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Is MiniCPM-V 4.6 1.3B open source?
Yes, MiniCPM-V 4.6 1.3B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
How many parameters does MiniCPM-V 4.6 1.3B have?
MiniCPM-V 4.6 1.3B has 1.3 billion parameters.
What is the license for MiniCPM-V 4.6 1.3B?
MiniCPM-V 4.6 1.3B is released under the Apache 2.0 license. This license allows commercial use.
How does MiniCPM-V 4.6 1.3B perform on benchmarks?
MiniCPM-V 4.6 1.3B achieves a score of 13 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Is MiniCPM-V 4.6 1.3B available via API?
MiniCPM-V 4.6 1.3B is an open weights model that can be self-hosted.
