AIbase
EN
Home
AI Models Finder
Mistral Large 2 (Nov '24)
M

Mistral Large 2 (Nov '24)

A large model with 123 billion parameters, excelling in code generation, mathematics, and reasoning. It supports enhanced multilingual capabilities, covering dozens of languages, has a 128k context window, and possesses advanced function call capabilities. It performs excellently in instruction following and provides concise outputs.
Intelligence(Relatively Weak)
Speed(Relatively Slow)
Input Supported Modalities
No
Is Reasoning Model
128,000
Context Window
128,000
Maximum Output Tokens
-
Knowledge Cutoff
Go Compare

Pricing

￥14.4 /M tokens
Input
￥43.2 /M tokens
Output
￥21.6 /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 Large 2 (Nov '24)Technical Parameters
Parameter Count
123,000.0M
Context Length
128.00k tokens
Training Data Cutoff
Open Source Category
Open Weights (License Required for Commercial Use)
Multimodal Support
Text Only
Throughput
42
Release Date
2024-11-18
Response Speed
57.028,225 tokens/s

Benchmark Scores

Below is the performance of Mistral Large 2 (Nov '24) in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
38.27
Large Language Model Intelligence Level
Coding Index
29.24
Indicator of AI model performance on coding tasks
Math Index
42.3
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
69.7
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
48.6
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
4
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
29.3
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
29.2
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
89.8
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
73.6
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
11
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