Model Comparison
Qwen3.7 Plus
vs. Qwen3 8B (Non-reasoning)
Comparing 2 AI models · 12 benchmarks · Alibaba
Recommended Pick
Al Qwen3.7 Plus 11 metric wins Strongest on: TTFT, Reasoning, Intelligence
Best Value
Qwen3 8B (Non-reasoning)
100.0 value score
30.6 reasoning / $0.18/1M
Lowest Price
Qwen3 8B (Non-reasoning)
$0.18/1M input price
Best Reasoning
Qwen3.7 Plus
58.9 reasoning score
Blends available reasoning benchmarks
Best for Coding
Qwen3.7 Plus
46.5 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
Qwen3 8B (Non-reasoning) has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
Qwen3 8B (Non-reasoning) is 2.2x cheaper on input tokens than Qwen3.7 Plus.
Speed gap
Qwen3 8B (Non-reasoning) generates about 1.2x as many tokens per second as Qwen3.7 Plus.
Reasoning gap
Qwen3.7 Plus leads Qwen3 8B (Non-reasoning) by 28.3 points on reasoning.
Coding gap
Qwen3.7 Plus leads Qwen3 8B (Non-reasoning) by 39.4 points on coding.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Qwen3.7 Plus
Alibaba
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Qwen3 8B (Non-reasoning)
Alibaba
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick Al Qwen3.7 Plus | Al Qwen3 8B (Non-reasoning) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.40/1M | $0.18/1M |
| Output Cost | $1.16/1M | $0.20/1M |
| Blended (3:1) | $0.59/1M | $0.18/1M |
| Specifications | ||
| Organization | Alibaba | Alibaba |
| Release Date | Jun 1, 2026 | Apr 28, 2025 |
| Performance & Speed | ||
| Throughput | 52.4 tok/s | 64.5 tok/s |
| TTFT | 1272ms | 1293ms |
| Latency | 39457ms | 1293ms |
| Composite Indices | ||
| Value Score | 60.3 | 100.0 |
| Reasoning Score | 58.9 | 30.6 |
| Intelligence | 53.3 | 10.6 |
| Coding | 46.5 | 7.1 |
| Math | — | 24.3 |
| Standard Benchmarks | ||
| GPQA | 90.0% | 45.2% |
| MMLU Pro | — | 64.3% |
| HLE | 33.4% | 2.8% |
| LiveCodeBench | — | 20.2% |
| MATH 500 | — | 82.8% |
| AIME 2025 | — | 24.3% |
| AIME (Original) | — | 24.3% |
| SciCode | 45.5% | 16.8% |
| LCR | 65.0% | 0.0% |
| IFBench | 78.0% | 28.6% |
| TAU-bench v2 | 93.0% | 24.9% |
| TerminalBench Hard | 47.0% | 2.3% |
Key Takeaways
Qwen3 8B (Non-reasoning) offers the best value at $0.18/1M, making it ideal for high-volume applications and cost-conscious projects.
Qwen3.7 Plus has the strongest reasoning profile with a 58.9 reasoning score, combining the available reasoning-heavy benchmarks.
Qwen3.7 Plus reaches a 46.5 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
Qwen3.7 Plus
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
Qwen3 8B (Non-reasoning)
- Cost-sensitive applications
- High-volume processing
