AIbase
EN
Home
AI Models Finder
Jamba 1.5 Mini
J

Jamba 1.5 Mini

As part of the Jamba 1.5 family, this is a state-of-the-art hybrid SSM-Transformer instruction-following base model that offers excellent long-context processing capabilities, speed, and quality. As a member of the Jamba 1.5 family, this is a cutting-edge hybrid SSM-Transformer instruction-following base model that excels at handling long contexts while being fast and delivering good results.
Intelligence(Weak)
Speed(Slow)
Input Supported Modalities
No
Is Reasoning Model
256,000
Context Window
256,144
Maximum Output Tokens
2024-03-05
Knowledge Cutoff
Go Compare

Pricing

￥1.44 /M tokens
Input
￥2.88 /M tokens
Output
￥1.8 /M tokens
Blended Price

Quick Simple Comparison

Input

Output

Jamba 1.7 Large
￥0.49
Jamba 1.7 Mini
Jamba 1.5 Mini
￥0.2

Basic Parameters

Jamba 1.5 MiniTechnical Parameters
Parameter Count
52,000.0M
Context Length
256.00k tokens
Training Data Cutoff
2024-03-05
Open Source Category
Open Weights (Permissive License)
Multimodal Support
Text Only
Throughput
100
Release Date
2024-08-22
Response Speed
0 tokens/s

Benchmark Scores

Below is the performance of Jamba 1.5 Mini in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
18.41
Large Language Model Intelligence Level
Coding Index
7.11
Indicator of AI model performance on coding tasks
Math Index
18.33
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
37.1
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
30.2
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
5.1
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
6.2
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
8
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
62.7
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
35.7
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
1
An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase