Devstral 2
Devstral 2 is Mistral AI’s code agent for demanding software engineering tasks. With 123 billion parameters, the model operates on codebase exploration, multi-file changes, debugging, and legacy modernization, supports a context window of 256,000 tokens, and processes both text and image inputs. Available as an Open Weights model under a modified MIT license, from a European provider environment with GDPR compliance.
- Open Weights
- Frontier
- Mistral AI
- Text
- Vision
- Long Context
- Interactive
Sovereign Risk: LOW Mistral AI is a French company headquartered in Paris, subject to EU GDPR and the AI Act. No known state influence risks. Model weights available.
Key metrics
Score · Latency · Cost · Quality
- Total Score Silver
- 70.19
- Routine
- 42.79
- Reasoning
- 27.39
- LLM Judge Avg
- 3.63 / 5
- 100 Coverage
- Avg Task Duration
- 22.91s
- Interactive
- Token Rate
- 56.23tok/s
- Output Rate
- P95 Latency
- 88.89s
- Top 5 %
- Total Tokens
- 57600
- Output Volume
- Cost per 1K
- $0.002
- USD / 1K Requests
- Benchmark Cost
- $0.12
- Total · 57600 tok
Benchmark modules
10 modules · weighted · vs. model median & top performer
Devstral 2
Best model
Ø All models
Code Quality
67.84
CLI Benchmark
80.34
Logical Reasoning
72.87
UX Writing
72.49
Documentation
70.21
Content Transform.
80.3
Cultural Intelligence
67.2
Synthesis Quality
43.33
Tool Execution
69.17
ToolUse Score
55.33
Benchmark Cost
$0.12
Token efficiency & latency
Consumption per module vs. model median
Token consumption per module
Performance profile
Key metrics – legend
Score
- Total Score
- Overall score derived from Routine and Reasoning scores. Basis for the fleet rank and tier assignment (Gold / Silver / Bronze).
- Routine
- Score for standard tasks: code generation, text transformation, structured outputs. Weighted by task complexity.
- Reasoning
- Score for analytical and logical tasks: multi-step problem solving, mathematical reasoning, structured argumentation.
- Rank
- Position in the fleet comparison, sorted by Total Score. Refers to the snapshot at the time of testing.
LLM Judge
- LLM Judge Ø
- Average quality rating by an independent judge model on a scale of 1–5.
- Coverage
- Share of tasks for which a judge rating is available. 100% means all responses were evaluated.
Latency & speed
- Avg. Task Duration
- Average time per task from the first to the last token of the response, measured across all benchmark tasks.
- Token Rate
- Output speed in tokens per second. Relevant for interactive applications and real-time streaming.
- P95 Latency
- 95th percentile of response times — shows outliers. Lower values mean fewer long wait times in edge cases.
Cost
- Cost per 1K
- API price per 1,000 output tokens in US dollars. Basis for cost calculation in production use.
- Benchmark Cost
- Total cost for the complete benchmark run of this model.