AIbase
EN
Home
AI Models Finder
Mistral Saba
M

Mistral Saba

Uniquely named model in Mistral's portfolio, potentially offering specialized capabilities. Based on Mistral's advanced architecture, optimized for specific use cases or market needs. Though specific functionality details are unclear, as part of Mistral series, expected to have company's consistent advantages in efficiency and performance, suitable for enterprise-grade applications and specialized task processing.
Intelligence(Relatively Weak)
Speed(Relatively Slow)
Input Supported Modalities
Yes
Is Reasoning Model
32,000
Context Window
-
Maximum Output Tokens
-
Knowledge Cutoff
Go Compare

Pricing

- /M tokens
Input
- /M tokens
Output
￥2.16 /M tokens
Blended Price

Quick Simple Comparison

Input

Output

Devstral
￥0.1
Devstral Medium
￥0.4
Devstral Small (May '25)
￥0.1

Basic Parameters

Mistral SabaTechnical Parameters
Parameter Count
Not Announced
Context Length
32.00k tokens
Training Data Cutoff
Open Source Category
Proprietary
Multimodal Support
Text Only
Throughput
Release Date
2025-02-17
Response Speed
97.02,589 tokens/s

Benchmark Scores

Below is the performance of Mistral Saba in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
34.09
Large Language Model Intelligence Level
Coding Index
-
Indicator of AI model performance on coding tasks
Math Index
40.33
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
61.1
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
42.4
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
4.1
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
-
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
24.1
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
85.4
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
67.7
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
13
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