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.
80
agents
0
multimodal
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
No ranking data available
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Code
HumanEvalOpenAI (2021)
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
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Reasoning80
General80
Code80
Pricing
No pricing data available
Speed
No speed data available
Provider Price Ranking
Provider Price Ranking
1 providers
ProviderInputOutput
1Mistral
$0.3
$0.9
Compare pricing across different API providers for this model.