Devstral Medium
MistralMistralProprietary
Description
Devstral Medium builds upon the strengths of Devstral Small and takes performance to the next level with a score of 61.6% on SWE-Bench Verified. Devstral Medium is available through the Mistral public API, and offers exceptional performance at a competitive price point, making it an ideal choice for businesses and developers looking for a high-quality, cost-effective model.
Release Date
2025-07-10
Parameters
—
Context Length
131K
Modalities
text
Capability Radar
32
general
23
coding
20
reasoning
33
scienceest.
0
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 272 | 29.0 | AA |
| General Ranking | 328 | 34.0 | AA |
| Math Reasoning | 313 | 18.0 | AA |
| Science | 320 | 34.0 | AA |
Benchmark Scores (LLM Stats)
Code
SWE-Bench Verified
61.6%SR
AA Evaluation Indices
Intelligence Index18.7
Coding Index15.9
Math Index4.7
Mmlu Pro0.7
Math 5000.7
Gpqa0.5
Livecodebench0.3
Ifbench0.3
Scicode0.3
Lcr0.3
Tau20.2
Terminalbench Hard0.1
Aime0.1
Aime 250.0
Hle0.0
LLM Stats Category Scores
Code60
Frontend Development60
Reasoning60
Pricing
Input Price$0.4 / 1M tokens
Output Price$2 / 1M tokens
Blended Price (3:1)$0.8 / 1M tokens
Speed
Tokens/sec78.3 tokens/s
Time to First Token0.49s
Time to Answer0.49s
Available Providers
(LS internal units)No provider data available