Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.
Added Aug 1, 2025
Context Window
256.0K
Max Output
32.8K
Input Price (Auto)
$0.30/1M
Output Price (Auto)
$0.90/1M
Cache Read (Auto)
$0.15/1M
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Design Arena.
Best Category
3D
Best Elo
1048
Best Rank Percentile
Top 86%
Ranking Distribution
6,734 battles
60%
45%
30%
15%
0%
5.8%
First
27.4%
Second
43.5%
Third
23.3%
Fourth
Category Performance
Models Arena
3D
1048
Elo
45.4%
Win
7.8s
Avg Time
#131
Rank
Data Visualization
1033
Elo
41.1%
Win
12.4s
Avg Time
#139
Rank
UI Component
1032
Elo
46.7%
Win
15.7s
Avg Time
#133
Rank
Website
1025
Elo
37.8%
Win
18.7s
Avg Time
#152
Rank
Game Development
990
Elo
36.3%
Win
14.9s
Avg Time
#148
Rank
Updated Sep 13, 2026, 12:22 PM · Matched as Codestral 2508
Design ArenaProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Codestral 2508 with similar models from the same provider or model family.
Mistral Small 3 24B (2501)
mistralai/mistral-small-24b-instruct-2501Mistral Small 3 24B (2501) hosted by IONOS in Berlin, Germany. Zero data retention.
Mistral Small 4 119B Thinking
mistralai/mistral-small-4-119b-2603:thinkingMistral Small 4 with reasoning enabled (reasoning_effort=high). A hybrid MoE model with deep step-by-step reasoning for complex prompts, coding, and multi-step problem solving.
Mistral Small 4 119B
mistralai/mistral-small-4-119b-2603Mistral Small 4 is a hybrid MoE model that unifies instruct, reasoning, and coding behavior in a single multimodal model. It supports text and image input, native function calling, JSON output, and per-request reasoning effort controls.
Mistral Large 3 675B
mistralai/mistral-large-3-675b-instruct-2512Mistral Large 3 675B is Mistral AI's flagship language model featuring advanced rope scaling and Eagle speculative decoding. Delivers exceptional performance across reasoning, coding, and multilingual tasks.
Mixtral 8x22B
mistralai/mixtral-8x22b-instruct-v0.1Mixtral 8x22B is a powerful sparse Mixture of Experts (MoE) model with 141B total parameters and 39B active per token. Features a 64K context window, exceptional math performance, and cost-efficient inference. Supports English, French, German, Spanish, and Italian. Apache 2.0 licensed.
Devstral 2 123B
mistralai/devstral-2-123b-instruct-2512Devstral 2 123B is a 123 billion parameter model from Mistral AI optimized for coding and development tasks. Features advanced reasoning capabilities for software engineering workflows.