Codestral 2508
Mistral AI · released Aug 1, 2025
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)
Specification
- Context window
- 256K
- Max output
- —
- Knowledge cutoff
- Mar 31, 2025
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- No
- Uptime
- 99.7%
Intelligence
—
Not benchmarked
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
49 t/s
Median across providers
Latency
208ms
Time to first token
Cost per task
$0.04
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
This model has not been put through the benchmark suite. Its speed, latency and pricing figures below are still measured.
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Claude Opus 5Anthropic63.1
- Claude Fable 5Anthropic62.1
- GPT-5.6 SolOpenAI60.9
- Kimi K3Moonshot AI59.7
- Qwen3.8 MaxQwen58.1
- Claude Opus 4.8Anthropic57.3
- Muse Spark 1.2Meta56.8
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Claude Opus 5 | 63.1 |
| Claude Fable 5 | 62.1 |
| GPT-5.6 Sol | 60.9 |
| Kimi K3 | 59.7 |
| Qwen3.8 Max | 58.1 |
| Claude Opus 4.8 | 57.3 |
| Muse Spark 1.2 | 56.8 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.3
- Output / 1M tokens
- $0.9
- Cached input / 1M
- $0.03
- Blended 3:1
- $0.45
One task, estimated
$0.04
- Input tokens
- 50,000
- Output tokens
- 25,000
- Profile
- Standard
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.
Arena
Head-to-head generation quality
Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.
- Overall Elo
- 1,075
- Win rate
- 45.5%
- Strongest at
- 3D scenes
- Tournaments
- 444
Elo by category
Dot position on a 1,000–1,075 scale · Elo has no meaningful zero
- 1,075
- 1,051
- 1,047
- 1,035
- 1,009
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| 3D scenes | 1075 | 45.5% |
| UI components | 1051 | 46.7% |
| Data visualisation | 1047 | 42.0% |
| Websites | 1035 | 37.8% |
| Game development | 1009 | 36.3% |