Mistral·Code — weighted competency·Tue 2 Jun 2026
MCodestral 3
Codestral 3 scores 72/100 competency for Code at $1.80.
Low confidenceOpen weights
Competency
72/100
category rank #6
Cost
$1.80/ 1M tokens
blended
Speed
82/100
Fast
Accuracy
3.5% halluc.
High confidence
Score history.
Weighted Code competency · last 12 weeks · weekly snapshot.
72/100
— flat
What it's actually good at.
Score on each business-task subset that goes into the weighted competency.
Test Generation10% of category weight
80
Code Generation40% of category weight
68
Review & Bug Fixing30% of category weight
72
Full-Repo Understanding20% of category weight
76
Best for. Watch out for.
✓ Best for
- Strong at Code Generation for Mistral.
- Strong at Review & Bug Fixing for Mistral.
⚠ Watch out for
- Validate fit for your specific workload before committing.
Pricing.
Published usage pricing. Figures refresh daily from our pricing sources.
$1.80
Usage pricing
$1.80/1M tok
- Input
- $1.80 / 1M tokens
- Output
- $5.40 / 1M tokens
Where it sits.
Position against the rest of the category. Ranked by weighted competency.
| Rank | Model | Score | Cost | Speed | Δ vs Codestral |
|---|---|---|---|---|---|
| 01 | OGPT-5 Code | 79 | $14.00 | 74 / 100 | +7 |
| 02 | DDeepSeek V3.1 Coder | 64 | $0.6 | 76 / 100 | -8 |
| 03 | AQwen 3 Coder | 48 | $1.40 | 78 / 100 | -24 |