Model Comparison
R1 (Jan '25)
vs. R1 Distill Qwen 32B
Comparing 2 AI models · 12 benchmarks · DeepSeek
Recommended Pick
De R1 (Jan '25) 11 metric wins Strongest on: Reasoning, Intelligence, Math
Lowest Price
R1 Distill Qwen 32B
$0.00/1M input price
Best Reasoning
R1 (Jan '25)
57.1 reasoning score
Blends available reasoning benchmarks
Best for Coding
R1 (Jan '25)
15.9 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
R1 Distill Qwen 32B is ∞x cheaper on input tokens than R1 (Jan '25).
Reasoning gap
R1 (Jan '25) leads R1 Distill Qwen 32B by 3.8 points on reasoning.
Top-pick rationale
R1 (Jan '25) wins 11 measurable categories, including Reasoning, Intelligence, Math, GPQA.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
R1 (Jan '25)
DeepSeek
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
R1 Distill Qwen 32B
DeepSeek
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick De R1 (Jan '25) | De R1 Distill Qwen 32B |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $1.68/1M | $0.00/1M |
| Output Cost | $4.70/1M | $0.00/1M |
| Blended (3:1) | $2.43/1M | — |
| Specifications | ||
| Organization | DeepSeek | DeepSeek |
| Release Date | Jan 20, 2025 | Jan 20, 2025 |
| Performance & Speed | ||
| Throughput | — | — |
| TTFT | — | — |
| Latency | — | — |
| Composite Indices | ||
| Value Score | 100.0 | — |
| Reasoning Score | 57.1 | 53.3 |
| Intelligence | 18.8 | 17.2 |
| Coding | 15.9 | — |
| Math | 68.0 | 63.0 |
| Standard Benchmarks | ||
| GPQA | 70.8% | 61.5% |
| MMLU Pro | 84.4% | 73.9% |
| HLE | 9.3% | 5.5% |
| LiveCodeBench | 61.7% | 27.0% |
| MATH 500 | 96.6% | 94.1% |
| AIME 2025 | 68.0% | 63.0% |
| AIME (Original) | 68.3% | 68.7% |
| SciCode | 35.7% | 37.6% |
| LCR | 52.3% | 9.7% |
| IFBench | 39.0% | 22.9% |
| TAU-bench v2 | 11.4% | — |
| TerminalBench Hard | 6.1% | — |
Key Takeaways
R1 Distill Qwen 32B offers the best value at $0.00/1M, making it ideal for high-volume applications and cost-conscious projects.
R1 (Jan '25) has the strongest reasoning profile with a 57.1 reasoning score, combining the available reasoning-heavy benchmarks.
R1 (Jan '25) reaches a 15.9 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
R1 (Jan '25)
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
R1 Distill Qwen 32B
- Cost-sensitive applications
- High-volume processing
