Model Comparison
R1 Distill Llama 8B
vs. Llama 3.2 Instruct 90B (Vision)
Comparing 2 AI models · 10 benchmarks · DeepSeek, Meta
Recommended Pick
De R1 Distill Llama 8B 9 metric wins Strongest on: Input price, Output price, TTFT
Lowest Price
R1 Distill Llama 8B
$0.00/1M input price
Best Reasoning
R1 Distill Llama 8B
35.4 reasoning score
Blends available reasoning benchmarks
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 Llama 8B is ∞x cheaper on input tokens than Llama 3.2 Instruct 90B (Vision).
Reasoning gap
R1 Distill Llama 8B leads Llama 3.2 Instruct 90B (Vision) by 9.8 points on reasoning.
Top-pick rationale
R1 Distill Llama 8B wins 9 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.
R1 Distill Llama 8B
DeepSeek
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Llama 3.2 Instruct 90B (Vision)
Meta
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick De R1 Distill Llama 8B | Me Llama 3.2 Instruct 90B (Vision) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.00/1M | $1.38/1M |
| Output Cost | $0.00/1M | $1.38/1M |
| Blended (3:1) | — | $1.38/1M |
| Specifications | ||
| Organization | DeepSeek | Meta |
| Release Date | Jan 20, 2025 | Sep 25, 2024 |
| Performance & Speed | ||
| Throughput | — | 46.1 tok/s |
| TTFT | — | 543ms |
| Latency | — | 543ms |
| Composite Indices | ||
| Value Score | — | 100.0 |
| Reasoning Score | 35.4 | 25.6 |
| Intelligence | 12.1 | 11.9 |
| Math | 41.3 | — |
| Standard Benchmarks | ||
| GPQA | 30.2% | 43.2% |
| MMLU Pro | 54.3% | 67.1% |
| HLE | 4.2% | 4.9% |
| LiveCodeBench | 23.3% | 21.4% |
| MATH 500 | 85.3% | 62.9% |
| AIME 2025 | 41.3% | — |
| AIME (Original) | 33.3% | 5.0% |
| SciCode | 11.9% | 24.0% |
| LCR | 0.0% | — |
| IFBench | 17.6% | — |
Key Takeaways
R1 Distill Llama 8B offers the best value at $0.00/1M, making it ideal for high-volume applications and cost-conscious projects.
R1 Distill Llama 8B has the strongest reasoning profile with a 35.4 reasoning score, combining the available reasoning-heavy benchmarks.
All models support context windows of ∞+ tokens, suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
R1 Distill Llama 8B
- Cost-sensitive applications
- High-volume processing
- Complex reasoning tasks
- Research & analysis
Llama 3.2 Instruct 90B (Vision)
- General-purpose AI
- Versatile applications
Recommended Comparisons
Popular alternatives 
