DataLearner logo
CO

Codestral 25.01

Coding model

Codestral 25.01

Release date: 2025-01-13Updated: 2025-01-14Views: 803
Live demoGitHubHugging FaceCompare
Parameters
No data
Context length
256K
Multilingual
No data
Reasoning ability
No data

Codestral 25.01 is an AI model published by MistralAI, released on 2025-01-13, for Coding model, and 256K context length, requiring about 0GB storage, with a 86.60 score on HumanEval.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Codestral 25.01

Model basics

Reasoning traces
No data
Thinking modes
Thinking modes not supported
Context length
256K tokens
Max output length
No data
Model type
Coding model
Modality (in / out)
No data
Release date
2025-01-13
Model file size
0GB
MoE architecture
No
Total params / Active params
No data / Not applicable
Knowledge cutoff
No data
Codestral 25.01

Open source & experience

Code license
Proprietary
Weights license
Proprietary
GitHub repo
N/A
Hugging Face
N/A
Live demo
N/A
Codestral 25.01

Official resources

Paper
N/A
DataLearnerAI blog
N/A
Codestral 25.01

API details

API speed
No data
No public API pricing yet.
Codestral 25.01

Benchmark Results

Codestral 25.01 currently shows benchmark results led by MBPP (11 / 70, score 80.20), HumanEval (20 / 101, score 86.60), LiveCodeBench (110 / 127, score 37.90). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

Coding and Software Engineer

3 evaluations
Benchmark / mode
Score
Rank/total
HumanEval
Standard Mode
86.60
20 / 101
MBPP
Standard Mode
80.20
11 / 70
LiveCodeBench
Standard Mode
37.90
110 / 127

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
Aider-Polyglot
Standard Mode
11.10
56 / 59
View benchmark analysisCompare with other models
Codestral 25.01

Publisher

Codestral 25.01

Model Overview

Codestral 25.01 is an AI model published by MistralAI, released on 2025-01-13, for Coding model, and 256K context length, requiring about 0GB storage, with a 86.60 score on HumanEval.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code