Codestral-22B
Mistral AIMistralOpen WeightMNPL-0.1
Description
A 22B parameter code generation model trained on 80+ programming languages including Python, Java, C, C++, JavaScript, and Bash. Supports both instruction-following and fill-in-the-middle (FIM) capabilities for code completion and generation tasks.
Release Date
2024-05-29
Parameters
22.2B
Context Length
—
Modalities
—
Capability Radar
80
general
80
coding
80
reasoning
68
scienceest.
0
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Reasoning | 69 | 57.0 | LS |
Benchmark Scores (LLM Stats)
Code
HumanEval
81.1%SR
RepoBench
34.0%SR
General
HumanEvalFIM-Average
91.6%SR
MBPP
0.78 / 100SR
Language
Spider
63.5%SR
Reasoning
HumanEval-Average
61.5%SR
CruxEval-O
51.3%SR
AA Evaluation Indices
No AA evaluation data available
LLM Stats Category Scores
Code80
General80
Reasoning80
Pricing
No pricing data available
Speed
No speed data available
Available Providers
(LS internal units)No provider data available