Codestral 25.08
Trained for code tasks, not for general use: Codestral 25.08 is Mistral AI’s specialized developer model from August 2025, optimized for fill-in-the-middle and a broad range of programming languages. With 22 billion parameters, it supports 128,000 tokens of context, runs either locally or via the Mistral API, but is subject to a restrictive license with limited commercial use.
- Restricted Weights
- Frontier
- Mistral AI
- Text
- Real-Time
Sovereign Risk: LOW Mistral AI is a French company headquartered in the EU and is not subject to any government access obligations regarding model weights such as the US CLOUD Act or China’s NSL.
Key metrics
Score · Latency · Cost · Quality
- Total Score Silver
- 65.48
- Routine
- 39.92
- Reasoning
- 25.56
- LLM Judge Avg
- 3.29 / 5
- 100 Coverage
- Avg Task Duration
- 3.8s
- Real-Time
- Token Rate
- 192.29tok/s
- Output Rate
- P95 Latency
- 11.64s
- Top 5 %
- Total Tokens
- 52600
- Output Volume
- Cost per 1K
- $0.0006
- USD / 1K Requests
- Benchmark Cost
- $0.03
- Total · 52600 tok
Benchmark modules
10 modules · weighted · vs. model median & top performer
Codestral 25.08
Best model
Ø All models
Code Quality
66.28
CLI Benchmark
84.34
Logical Reasoning
64.11
UX Writing
60.77
Documentation
62.72
Content Transform.
64.2
Cultural Intelligence
62
Synthesis Quality
56.67
Tool Execution
83.33
ToolUse Score
68.83
Benchmark Cost
$0.03
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.