AIbase
EN
Home
AI Models Finder
Mistral 7B Instruct
M

Mistral 7B Instruct

7B parameter instruction-tuned model from Mistral AI, famous for excellent performance-price ratio. Though relatively small in parameter scale, achieves beyond-scale performance through careful architectural design and training strategies. This model became popular choice in open-source community, demonstrating importance of efficient model design, suitable for various applications requiring balanced performance and resources.
Intelligence(Weak)
Speed(Medium)
Input Supported Modalities
Yes
Is Reasoning Model
8,192
Context Window
-
Maximum Output Tokens
-
Knowledge Cutoff
Go Compare

Pricing

- /M tokens
Input
- /M tokens
Output
￥1.8 /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 7B InstructTechnical Parameters
Parameter Count
Not Announced
Context Length
8,192 tokens
Training Data Cutoff
Open Source Category
Open Weights (Permissive License)
Multimodal Support
Text Only
Throughput
Release Date
2023-09-27
Response Speed
121.93,663 tokens/s

Benchmark Scores

Below is the performance of Mistral 7B Instruct in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
10.14
Large Language Model Intelligence Level
Coding Index
3.49
Indicator of AI model performance on coding tasks
Math Index
6.07
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
24.5
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
17.7
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
4.3
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
4.6
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
2.4
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
40.2
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
12.1
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
-
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