Model Comparison
V3.1 Terminus (Reasoning)
vs. Medium 3
Comparing 2 AI models · 12 benchmarks · DeepSeek, Mistral
Recommended Pick
De V3.1 Terminus (Reasoning) 16 metric wins Strongest on: TTFT, Latency, Reasoning
Best Value
Medium 3
100.0 value score
39.5 reasoning / $0.80/1M
Lowest Price
Medium 3
$0.40/1M input price
Best Reasoning
V3.1 Terminus (Reasoning)
61.5 reasoning score
Blends available reasoning benchmarks
Best for Coding
V3.1 Terminus (Reasoning)
33.7 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 has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
Medium 3 is 4.1x cheaper on input tokens than V3.1 Terminus (Reasoning).
Reasoning gap
V3.1 Terminus (Reasoning) leads Medium 3 by 22.1 points on reasoning.
Coding gap
V3.1 Terminus (Reasoning) leads Medium 3 by 20.1 points on coding.
Top-pick rationale
V3.1 Terminus (Reasoning) wins 16 measurable categories, including TTFT, Latency, Reasoning, Intelligence.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
V3.1 Terminus (Reasoning)
DeepSeek
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Medium 3
Mistral
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick De V3.1 Terminus (Reasoning) | Mi Medium 3 |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $1.64/1M | $0.40/1M |
| Output Cost | $2.75/1M | $2.00/1M |
| Blended (3:1) | $1.91/1M | $0.80/1M |
| Specifications | ||
| Organization | DeepSeek | Mistral |
| Release Date | Sep 22, 2025 | May 7, 2025 |
| Performance & Speed | ||
| Throughput | — | 46.9 tok/s |
| TTFT | — | 521ms |
| Latency | — | 521ms |
| Composite Indices | ||
| Value Score | 65.2 | 100.0 |
| Reasoning Score | 61.5 | 39.5 |
| Intelligence | 33.9 | 18.8 |
| Coding | 33.7 | 13.6 |
| Math | 89.7 | 30.3 |
| Standard Benchmarks | ||
| GPQA | 79.2% | 57.8% |
| MMLU Pro | 85.1% | 76.0% |
| HLE | 15.2% | 4.3% |
| LiveCodeBench | 79.8% | 40.0% |
| MATH 500 | — | 90.7% |
| AIME 2025 | 89.7% | 30.3% |
| AIME (Original) | — | 44.0% |
| SciCode | 40.6% | 33.1% |
| LCR | 65.0% | 28.0% |
| IFBench | 57.0% | 39.3% |
| TAU-bench v2 | 37.1% | 24.3% |
| TerminalBench Hard | 30.3% | 3.8% |
Key Takeaways
Medium 3 offers the best value at $0.40/1M, making it ideal for high-volume applications and cost-conscious projects.
V3.1 Terminus (Reasoning) has the strongest reasoning profile with a 61.5 reasoning score, combining the available reasoning-heavy benchmarks.
V3.1 Terminus (Reasoning) reaches a 33.7 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
V3.1 Terminus (Reasoning)
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
Medium 3
- Cost-sensitive applications
- High-volume processing
