Model Comparison
Medium
vs. Medium 3.5
Comparing 2 AI models · 11 benchmarks · Mistral
Recommended Pick
Mi Medium 3.5 9 metric wins Strongest on: Value, Input price, Output price
Best Value
Medium 3.5
100.0 value score
39.2 reasoning / $3.00/1M
Lowest Price
Medium 3.5
$1.50/1M input price
Best Reasoning
Medium 3.5
39.2 reasoning score
Blends available reasoning benchmarks
Best for Coding
Medium 3.5
35.4 coding index
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Best value
Medium 3.5 has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
Medium 3.5 is 1.8x cheaper on input tokens than Medium.
Speed gap
Medium generates about 1.3x as many tokens per second as Medium 3.5.
Reasoning gap
Medium 3.5 leads Medium by 22.0 points on reasoning.
Top-pick rationale
Medium 3.5 wins 9 measurable categories, including Value, Input price, Output price, Blended price.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Medium
Mistral
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Medium 3.5
Mistral
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Mi Medium | Top Pick Mi Medium 3.5 |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $2.75/1M | $1.50/1M |
| Output Cost | $8.10/1M | $7.50/1M |
| Blended (3:1) | $4.09/1M | $3.00/1M |
| Specifications | ||
| Organization | Mistral | Mistral |
| Release Date | Dec 11, 2023 | Apr 29, 2026 |
| Performance & Speed | ||
| Throughput | 88.2 tok/s | 67.1 tok/s |
| TTFT | 606ms | 657ms |
| Latency | 606ms | 30461ms |
| Composite Indices | ||
| Value Score | 32.2 | 100.0 |
| Reasoning Score | 17.2 | 39.2 |
| Intelligence | 3.6 | 29.9 |
| Coding | — | 35.4 |
| Standard Benchmarks | ||
| GPQA | 34.9% | 74.8% |
| MMLU Pro | 49.1% | — |
| HLE | 3.4% | 12.8% |
| LiveCodeBench | 9.9% | — |
| MATH 500 | 40.5% | — |
| AIME (Original) | 3.7% | — |
| SciCode | 11.8% | 39.6% |
| LCR | — | 61.0% |
| IFBench | — | 68.8% |
| TAU-bench v2 | — | 94.2% |
| TerminalBench Hard | — | 33.3% |
Key Takeaways
Medium 3.5 offers the best value at $1.50/1M, making it ideal for high-volume applications and cost-conscious projects.
Medium 3.5 has the strongest reasoning profile with a 39.2 reasoning score, combining the available reasoning-heavy benchmarks.
Medium 3.5 reaches a 35.4 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
Medium
- General-purpose AI
- Versatile applications
Medium 3.5
- Cost-sensitive applications
- High-volume processing
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
