Model Comparison
Qwen3.7 Plus
vs. Qwen3 Max Thinking (Preview)
Comparing 2 AI models · 10 benchmarks · Alibaba
Recommended Pick
Al Qwen3.7 Plus 15 metric wins Strongest on: Value, Input price, Output price
Best Value
Qwen3.7 Plus
100.0 value score
58.9 reasoning / $0.59/1M
Lowest Price
Qwen3.7 Plus
$0.40/1M 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
Qwen3.7 Plus has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
Qwen3.7 Plus is 3.0x cheaper on input tokens than Qwen3 Max Thinking (Preview).
Reasoning gap
Qwen3.7 Plus leads Qwen3 Max Thinking (Preview) by 1.6 points on reasoning.
Coding gap
Qwen3.7 Plus leads Qwen3 Max Thinking (Preview) by 22.0 points on coding.
Top-pick rationale
Qwen3.7 Plus wins 15 measurable categories, including Value, Input price, Output price, Blended price.
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 Max Thinking (Preview)
Alibaba
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick Al Qwen3.7 Plus | Al Qwen3 Max Thinking (Preview) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.40/1M | $1.20/1M |
| Output Cost | $1.16/1M | $6.00/1M |
| Blended (3:1) | $0.59/1M | $2.40/1M |
| Specifications | ||
| Organization | Alibaba | Alibaba |
| Release Date | Jun 1, 2026 | Nov 3, 2025 |
| Performance & Speed | ||
| Throughput | 52.4 tok/s | 54.9 tok/s |
| TTFT | 1273ms | 1727ms |
| Latency | 39452ms | 38129ms |
| Composite Indices | ||
| Value Score | 100.0 | 23.9 |
| Reasoning Score | 58.9 | 57.3 |
| Intelligence | 53.3 | 32.5 |
| Coding | 46.5 | 24.5 |
| Math | — | 82.3 |
| Standard Benchmarks | ||
| GPQA | 90.0% | 77.6% |
| MMLU Pro | — | 82.4% |
| HLE | 33.4% | 12.0% |
| LiveCodeBench | — | 53.5% |
| AIME 2025 | — | 82.3% |
| SciCode | 45.5% | 38.7% |
| LCR | 65.0% | 57.7% |
| IFBench | 78.0% | 53.8% |
| TAU-bench v2 | 93.0% | 83.6% |
| TerminalBench Hard | 47.0% | 17.4% |
Key Takeaways
Qwen3.7 Plus offers the best value at $0.40/1M, 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
- Cost-sensitive applications
- High-volume processing
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
Qwen3 Max Thinking (Preview)
- General-purpose AI
- Versatile applications
