Model Comparison
Qwen3 Max (Preview)
vs. Step 3.7 Flash
Comparing 2 AI models · 10 benchmarks · Alibaba, StepFun
Recommended Pick
St Step 3.7 Flash 15 metric wins Strongest on: Value, Input price, Output price
Best Value
Step 3.7 Flash
100.0 value score
47.8 reasoning / $0.44/1M
Lowest Price
Step 3.7 Flash
$0.20/1M input price
Best Reasoning
Qwen3 Max (Preview)
52.4 reasoning score
Blends available reasoning benchmarks
Best for Coding
Step 3.7 Flash
37.1 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
Step 3.7 Flash has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
Step 3.7 Flash is 6.0x cheaper on input tokens than Qwen3 Max (Preview).
Speed gap
Step 3.7 Flash generates about 6.8x as many tokens per second as Qwen3 Max (Preview).
Reasoning gap
Qwen3 Max (Preview) leads Step 3.7 Flash by 4.6 points on reasoning.
Coding gap
Step 3.7 Flash leads Qwen3 Max (Preview) by 11.6 points on coding.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Qwen3 Max (Preview)
Alibaba
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Step 3.7 Flash
StepFun
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Al Qwen3 Max (Preview) | Top Pick St Step 3.7 Flash |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $1.20/1M | $0.20/1M |
| Output Cost | $6.00/1M | $1.15/1M |
| Blended (3:1) | $2.40/1M | $0.44/1M |
| Specifications | ||
| Organization | Alibaba | StepFun |
| Release Date | Sep 5, 2025 | May 29, 2026 |
| Performance & Speed | ||
| Throughput | 59.8 tok/s | 406.6 tok/s |
| TTFT | 1753ms | 718ms |
| Latency | 1753ms | 5636ms |
| Composite Indices | ||
| Value Score | 20.0 | 100.0 |
| Reasoning Score | 52.4 | 47.8 |
| Intelligence | 26.1 | 42.6 |
| Coding | 25.5 | 37.1 |
| Math | 75.0 | — |
| Standard Benchmarks | ||
| GPQA | 76.4% | 80.9% |
| MMLU Pro | 83.8% | — |
| HLE | 9.3% | 19.9% |
| LiveCodeBench | 65.1% | — |
| AIME 2025 | 75.0% | — |
| SciCode | 37.0% | 40.0% |
| LCR | 39.7% | 63.7% |
| IFBench | 48.0% | 67.3% |
| TAU-bench v2 | 32.7% | 98.5% |
| TerminalBench Hard | 19.7% | 35.6% |
Key Takeaways
Step 3.7 Flash offers the best value at $0.20/1M, making it ideal for high-volume applications and cost-conscious projects.
Qwen3 Max (Preview) has the strongest reasoning profile with a 52.4 reasoning score, combining the available reasoning-heavy benchmarks.
Step 3.7 Flash reaches a 37.1 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 Max (Preview)
- Complex reasoning tasks
- Research & analysis
Step 3.7 Flash
- Cost-sensitive applications
- High-volume processing
- Code generation
- Software development
