Model Comparison
R1 0528 Qwen3 8B
vs. Large 3
Comparing 2 AI models · 12 benchmarks · DeepSeek, Mistral
Recommended Pick
Mi Large 3 10 metric wins Strongest on: Throughput, Intelligence, Coding
Lowest Price
R1 0528 Qwen3 8B
$0.00/1M input price
Best Reasoning
R1 0528 Qwen3 8B
52.7 reasoning score
Blends available reasoning benchmarks
Best for Coding
Large 3
22.7 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 0528 Qwen3 8B is ∞x cheaper on input tokens than Large 3.
Reasoning gap
R1 0528 Qwen3 8B leads Large 3 by 18.5 points on reasoning.
Coding gap
Large 3 leads R1 0528 Qwen3 8B by 14.9 points on coding.
Top-pick rationale
Large 3 wins 10 measurable categories, including Throughput, Intelligence, Coding, GPQA.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
R1 0528 Qwen3 8B
DeepSeek
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Large 3
Mistral
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | De R1 0528 Qwen3 8B | Top Pick Mi Large 3 |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.00/1M | $0.50/1M |
| Output Cost | $0.00/1M | $1.50/1M |
| Blended (3:1) | — | $0.75/1M |
| Specifications | ||
| Organization | DeepSeek | Mistral |
| Release Date | May 29, 2025 | Dec 2, 2025 |
| Performance & Speed | ||
| Throughput | — | 66.5 tok/s |
| TTFT | — | 551ms |
| Latency | — | 551ms |
| Composite Indices | ||
| Value Score | — | 100.0 |
| Reasoning Score | 52.7 | 34.2 |
| Intelligence | 16.4 | 22.8 |
| Coding | 7.8 | 22.7 |
| Math | 63.7 | 38.0 |
| Standard Benchmarks | ||
| GPQA | 61.2% | 68.0% |
| MMLU Pro | 73.9% | 80.7% |
| HLE | 5.6% | 4.1% |
| LiveCodeBench | 51.3% | 46.5% |
| MATH 500 | 93.2% | — |
| AIME 2025 | 63.7% | 38.0% |
| AIME (Original) | 65.0% | — |
| SciCode | 20.4% | 36.2% |
| LCR | 13.0% | 34.7% |
| IFBench | 19.9% | 36.2% |
| TAU-bench v2 | 0.0% | 24.6% |
| TerminalBench Hard | 1.5% | 15.9% |
Key Takeaways
R1 0528 Qwen3 8B offers the best value at $0.00/1M, making it ideal for high-volume applications and cost-conscious projects.
R1 0528 Qwen3 8B has the strongest reasoning profile with a 52.7 reasoning score, combining the available reasoning-heavy benchmarks.
Large 3 reaches a 22.7 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
R1 0528 Qwen3 8B
- Cost-sensitive applications
- High-volume processing
- Complex reasoning tasks
- Research & analysis
Large 3
- Code generation
- Software development
