Mistral AI
Devstral Small
Tool calling
Mistral coding agent model for repository tasks and software engineering workflows
- Context
- 128K
- Released
- 1y ago
- Parameters
- —
Sources:models.dev
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- Mistral AI
- Model family
- Devstral
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- July 10, 2025
- Model ID
mistral/devstral-small-2507- Openness
- Open weights
- License
- —
- Parameters
- —
- Input modalities
- text
- Output modalities
- text
- Modality
- text->text
- Max output tokens
- 128K
- Knowledge cutoff
- 2025-05
- Hugging Face
- —
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- mistral/devstral-small-2507
- Source family
- devstral
- Last updated
- 2025-07-10
- Knowledge cutoff
- 2025-05
- Model context
- 128K
- Model output limit
- 128K
- Open weights
- Yes
- File attachments
- No
- Reasoning
- No
- Tool calling
- Yes
- Temperature control
- Yes
Downloadable weights
Published benchmarks
| Benchmark | Score | Evaluation details | Evidence |
|---|---|---|---|
| SWE-Bench Verified | 53.6 · resolved | 2025-07-10 | Source |
Complete source record (JSON)
{
"id": "mistral/devstral-small-2507",
"name": "Devstral Small",
"description": "Mistral coding agent model for repository tasks and software engineering workflows",
"family": "devstral",
"last_updated": "2025-07-10",
"knowledge": "2025-05",
"attachment": false,
"reasoning": false,
"tool_call": true,
"temperature": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 128000
},
"benchmarks": [
{
"name": "SWE-Bench Verified",
"score": 53.6,
"source": "https://mistral.ai/news/devstral-2507",
"metric": "resolved",
"date": "2025-07-10"
}
],
"release_date": "2025-07-10",
"open_weights": true,
"weights": [
{
"label": "Hugging Face",
"url": "https://huggingface.co/mistralai/Devstral-Small-2507"
}
]
}Infrastructure
Provider availability
Provider endpoint data will appear after this model's first OpenRouter endpoint sync.
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.