Intelligence
18
score
Magistral Medium 1.2 scores 18 on the Artificial Analysis Intelligence Index, placing it below …
vs class avg: 28
Mistral•Open weights•September 18, 2025
Magistral Medium 1.2
Intelligence, Performance & Price Analysis
Source:Artificial Analysis scrapeType:Open weights
Speed
39.6
output tokens/sec
Magistral Medium 1.2 generates output at 39.6 tokens per second (based on Mistral's API), which is …
Latency
1.77s
TTFT
Magistral Medium 1.2 has a time to first token (TTFT) of 1.77s (based on Mistral's API), which is …
Input Price#95/169
$2.00
/ 1M tokens
Magistral Medium 1.2 costs $2.00 per 1M input tokens (somewhat higher than average, median: $1. …
Output Price#57/169
$5.00
/ 1M tokens
Magistral Medium 1.2 costs $2.00 per 1M input tokens (somewhat higher than average, median: $1. …
Decision Overview
Ethen's intelligence-driven routing assessment for this model
Overall verdict
Capable everyday model
Good for routine tasks; route complex reasoning and premium workloads to stronger models.
Best for
- Routine Q&A
- Content summarization
- Classification
- Light coding
- High-value tasks where quality outweighs cost
Weak or unsuitable
- Complex reasoning
- Agentic workflows
- Research-grade analysis
- Routine high-volume generation
- Simple extraction or labeling
Routing recommendation
1
Cheaper routes for predictable extraction, labeling, or summarization
2
Cache-backed reuse for repeated prompts
Cost pressure
Premium pricing — $2.00 / M input, $5.00 / M output. Use cheaper routes for repetitive or low-risk work.
Model-fit matrix
Use this model where capability pays for itself; route away where volume, latency, or budget dominate.
| Use case | Fit | Reason | Routing note |
|---|---|---|---|
| Complex reasoning & agentic workflows | Moderate | Intelligence score 18 handles routine reasoning but may struggle with open-ended agentic tasks. | Route simpler sub-tasks here; keep hard reasoning on a stronger model. |
| High-volume chat & customer-facing | Moderate | Output speed may be a bottleneck for real-time chat at scale. | Consider a faster model for latency-sensitive chat. |
| Latency-sensitive applications | Strong | TTFT 1.77s — adequate latency for most interactive use cases. | Suitable for real-time; test with your specific workload. |
| Cost-sensitive pipelines | Moderate | Output pricing at $5.00 is premium. Route high-volume simple tasks to cheaper alternatives. | Use only for high-value tasks; route simple queries to budget models. |
Cost pressure
HighPricing is premium — input $2.00, output $5.00. This model is expensive for high-volume or output-heavy workloads.
Cheaper substitutes
- Lower-cost models for repetitive or high-volume work
- Cache-backed reuse for repeated prompts
Route away when
- Output-heavy tasks
- High-frequency chat at scale
- Simple queries that cheaper models handle well
Highlights
Key benchmark results at a glance.
Intelligence
Intelligence position
Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis
Magistral Medium 1.2 scores 18 on the Artificial Analysis Intelligence Index, placing it below average among other reasoning models in a similar price tier (median: 28).
Speed
Speed position
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Magistral Medium 1.2 generates output at 39.6 tokens per second (based on Mistral's API), which is at the lower end compared to other reasoning models in a similar price tier (median: 81.2 t/s).
Context, Cost & Pricing
Price/value position
Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis
Pricing is premium — input $2.00, output $5.00. This model is expensive for high-volume or output-heavy workloads.
Intelligence & Quality
Benchmark scores and quality indices measuring model capability.
AA-Omniscience Index
AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis
Source and methodology are summarized below
Chart source and provenance are listed in Methodology & sources below.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Source and methodology are summarized below
Chart source and provenance are listed in Methodology & sources below.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Source and methodology are summarized below
Chart source and provenance are listed in Methodology & sources below.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis
Source and methodology are summarized below
Chart source and provenance are listed in Methodology & sources below.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Speed & Throughput
Output tokens per second and generation throughput.
Output Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Source and methodology are summarized below
Chart source and provenance are listed in Methodology & sources below.
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Source and methodology are summarized below
Chart source and provenance are listed in Methodology & sources below.
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
Latency & Response Time
Time to first token and end-to-end response latency.
End-to-End Response Time
Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · Evaluation results measured independently by Artificial Analysis
Source and methodology are summarized below
Chart source and provenance are listed in Methodology & sources below.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Latency: Time To First Answer Token
Seconds to first answer token received · Accounts for reasoning model 'thinking' time · Evaluation results measured independently by Artificial Analysis
Source and methodology are summarized below
Chart source and provenance are listed in Methodology & sources below.
Latency includes thinking / reasoning time when applicable. Lower is better for interactive use cases.
Context, Cost & Pricing
Context window size, cost per task, and token pricing.
Context Window
Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis
Source and methodology are summarized below
Chart source and provenance are listed in Methodology & sources below.
Larger context windows enable complex multi-turn tasks but may increase latency and cost for long inputs.
Cost per Intelligence Index Task
Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better · Evaluation results measured independently by Artificial Analysis
Source and methodology are summarized below
Chart source and provenance are listed in Methodology & sources below.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost per Task
Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis
Source and methodology are summarized below
Chart source and provenance are listed in Methodology & sources below.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost to Run Artificial Analysis Intelligence Index
Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
Source and methodology are summarized below
Chart source and provenance are listed in Methodology & sources below.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Pricing: Cache Hit, Input, and Output
Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis
Source and methodology are summarized below
Chart source and provenance are listed in Methodology & sources below.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Time per Intelligence Index Task
Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better · Evaluation results measured independently by Artificial Analysis
Source and methodology are summarized below
Chart source and provenance are listed in Methodology & sources below.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Additional Benchmarks
Further benchmark and comparison data.
Output Tokens per Intelligence Index Task
Weighted average number of output tokens used to run one task in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
Source and methodology are summarized below
Chart source and provenance are listed in Methodology & sources below.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Specifications
Technical Specifications
Magistral Medium 1.2 scores 18 on the Artificial Analysis Intelligence Index, placing it below average among other reasoning models in a similar price tier (median: 28). Magistral Medium 1.2 generates output at 39.6 tokens per second (based on Mistral's API), which is at the lower end compared to other reasoning models in a similar price tier (median: 81.2 t/s). Magistral Medium 1.2 costs $2.00 per 1M input tokens (somewhat higher than average, median: $1.50) and $5.00 per 1M output tokens (better than average, median: $8.40), based on Mistral's API.
Magistral Medium 1.2
- Model type
- Open weights
- Reasoning
- Yes
- Input modalities
- Magistral Medium 1.2 supports text and image input.
- Output modalities
- Magistral Medium 1.2 supports text output.
- Context window
- 130k tokens
- Open weights / source
- No, Magistral Medium 1.2 is proprietary. The model weights are not publicly available.
- Parameters
- Magistral Medium 1.2 is a proprietary model and Mistral has not disclosed the model size or parameter count.
- API availability
- Yes, Magistral Medium 1.2 is available via API through 1 provider.
Methodology & Provenance
This page is rendered from the normalized profile and page JSON for Magistral Medium 1.2.
Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.
Source file: md/scrape/artificial_analysis_model_pages/artificialanalysis_ai__models__magistral-medium-2509__222a6caac5.html · Canonical URL: https://artificialanalysis.ai/models/magistral-medium-2509
Normalized at: 2026-07-08T03:24:56+00:00 Technical specs, comparison summary, and FAQs are passed through from the normalized data without rewriting.
Ranks shown on summary cards come directly from the normalized profile. No rank or class display is synthesized in the renderer.
Visible FAQ answers and FAQ JSON-LD are emitted from the same normalized FAQ array, so structured data stays aligned with the rendered accordion.
Time per Intelligence Index Task: https://artificialanalysis.ai/models/magistral-medium-2509
Frequently Asked Questions
Magistral Medium 1.2 was released on September 18, 2025.
Magistral Medium 1.2 was created by Mistral.
Magistral Medium 1.2 scores 18 on the Artificial Analysis Intelligence Index, placing it below average among other reasoning models in a similar price tier (median: 28).