Jamba 1.7 Mini
Intelligence
8.1
#488/523
Coding
3.1
#398/429
Math
0.3
#264/265
Speed
—
Pricing
—
Jamba 1.7 Mini is AI21 Labs’ latest model designed for various natural language processing tasks. It features an Intelligence Index of 8.1, making it suitable for applications requiring advanced understanding of context and semantics.
When to Use Jamba 1.7 Mini
✓ Best For
- Text generation and summarization.
- Conversational AI applications.
- Content creation for marketing and social media.
✗ Not Ideal For
- Complex mathematical problem-solving.
- High-speed processing needs due to unspecified speed metrics.
How Jamba 1.7 Mini Compares
Intelligence Index · Higher is better
Allen Institute for AILG AI ResearchAI21 LabsLiquid AI
Benchmark Profile
Coding Index
IBMLG AI ResearchAI21 LabsMicrosoft
Math Index
Allen Institute for AIMicrosoftAI21 Labs
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (14)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 8.1 | |
| Coding Index | 3.1 | |
| Math Index | 0.3 | |
| MMLU-Pro | 388% | |
| GPQA | 322% | |
| LiveCodeBench | 61% | |
| HLE | 45% | |
| SciCode | 9.3% | |
| IFBench | 31.4% | |
| LCR | 12.7% | |
| Tau2 | 12.6% | |
| AIME | 1.3% | |
| AIME 2025 | 0.3% | |
| MATH 500 | 25.8% |
Data: Artificial Analysis · Updated: March 27, 2026
Frequently Asked Questions (15)
When was Jamba 1.7 Mini released?
Jamba 1.7 Mini was released on July 7, 2025.
Who created Jamba 1.7 Mini?
Jamba 1.7 Mini was created by AI21 Labs.
How intelligent is Jamba 1.7 Mini?
Jamba 1.7 Mini scores 8 on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 13).
How verbose is Jamba 1.7 Mini?
When evaluated on the Intelligence Index, Jamba 1.7 Mini generated 5.3M output tokens, which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 3.8M).
Is Jamba 1.7 Mini a reasoning model?
No, Jamba 1.7 Mini is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Jamba 1.7 Mini support?
Jamba 1.7 Mini supports text input.
What output modalities does Jamba 1.7 Mini support?
Jamba 1.7 Mini supports text output.
Can Jamba 1.7 Mini process images?
No, Jamba 1.7 Mini does not support image input. It can only process text.
Is Jamba 1.7 Mini multimodal?
No, Jamba 1.7 Mini is not multimodal. It only supports text input.
What is the context window of Jamba 1.7 Mini?
Jamba 1.7 Mini has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Is Jamba 1.7 Mini open source?
Yes, Jamba 1.7 Mini is open weights. The model weights are publicly available and can be downloaded for self-hosting.
How many parameters does Jamba 1.7 Mini have?
Jamba 1.7 Mini has 52 billion parameters (12 billion active).
What are the active parameters of Jamba 1.7 Mini?
Jamba 1.7 Mini is a Mixture of Experts (MoE) model with 52 billion total parameters, but only 12 billion active parameters are used during inference.
What is the license for Jamba 1.7 Mini?
Jamba 1.7 Mini is released under the Jamba Open Model License Agreement license. This license allows commercial use.
How does Jamba 1.7 Mini perform on benchmarks?
Jamba 1.7 Mini achieves a score of 8 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
