Model Comparison
Magistral Small 1
vs. Small 3.2
Comparing 2 AI models · 12 benchmarks · Mistral
Recommended Pick
Mi Magistral Small 1 14 metric wins Strongest on: Input price, Output price, TTFT
Lowest Price
Magistral Small 1
$0.00/1M input price
Best Reasoning
Magistral Small 1
48.3 reasoning score
Blends available reasoning benchmarks
Best for Coding
Small 3.2
13.3 coding index
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Price gap
Magistral Small 1 is ∞x cheaper on input tokens than Small 3.2.
Reasoning gap
Magistral Small 1 leads Small 3.2 by 13.4 points on reasoning.
Coding gap
Small 3.2 leads Magistral Small 1 by 2.2 points on coding.
Top-pick rationale
Magistral Small 1 wins 14 measurable categories, including Input price, Output price, TTFT, Latency.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Magistral Small 1
Mistral
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Small 3.2
Mistral
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick Mi Magistral Small 1 | Mi Small 3.2 |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.00/1M | $0.09/1M |
| Output Cost | $0.00/1M | $0.25/1M |
| Blended (3:1) | — | $0.13/1M |
| Specifications | ||
| Organization | Mistral | Mistral |
| Release Date | Jun 10, 2025 | Jun 20, 2025 |
| Performance & Speed | ||
| Throughput | — | 131.2 tok/s |
| TTFT | — | 396ms |
| Latency | — | 396ms |
| Composite Indices | ||
| Value Score | — | 100.0 |
| Reasoning Score | 48.3 | 34.9 |
| Intelligence | 16.8 | 15.1 |
| Coding | 11.1 | 13.3 |
| Math | 41.3 | 27.0 |
| Standard Benchmarks | ||
| GPQA | 64.1% | 50.5% |
| MMLU Pro | 74.6% | 68.1% |
| HLE | 7.2% | 4.3% |
| LiveCodeBench | 51.4% | 27.5% |
| MATH 500 | 96.3% | 88.3% |
| AIME 2025 | 41.3% | 27.0% |
| AIME (Original) | 71.3% | 32.3% |
| SciCode | 24.1% | 26.4% |
| LCR | 0.0% | 17.3% |
| IFBench | 24.8% | 33.5% |
| TAU-bench v2 | 26.6% | 29.5% |
| TerminalBench Hard | 4.5% | 6.8% |
Key Takeaways
Magistral Small 1 offers the best value at $0.00/1M, making it ideal for high-volume applications and cost-conscious projects.
Magistral Small 1 has the strongest reasoning profile with a 48.3 reasoning score, combining the available reasoning-heavy benchmarks.
Small 3.2 reaches a 13.3 coding index, making it the top choice for software development and code generation tasks.
All models support context windows of ∞+ tokens, suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
Magistral Small 1
- Cost-sensitive applications
- High-volume processing
- Complex reasoning tasks
- Research & analysis
Small 3.2
- Code generation
- Software development
