Model Comparison
30B (high)
vs. Step 3.7 Flash
Comparing 2 AI models · 7 benchmarks · Sarvam, StepFun
Recommended Pick
St Step 3.7 Flash 13 metric wins Strongest on: Throughput, TTFT, Latency
Best Value
30B (high)
100.0 value score
27.5 reasoning / $0.05/1M
Lowest Price
30B (high)
$0.03/1M input price
Best Reasoning
Step 3.7 Flash
47.8 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
30B (high) has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
30B (high) is 7.7x cheaper on input tokens than Step 3.7 Flash.
Speed gap
Step 3.7 Flash generates about 1.7x as many tokens per second as 30B (high).
Reasoning gap
Step 3.7 Flash leads 30B (high) by 20.3 points on reasoning.
Coding gap
Step 3.7 Flash leads 30B (high) by 29.2 points on coding.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
30B (high)
Sarvam
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 | Sa 30B (high) | Top Pick St Step 3.7 Flash |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.03/1M | $0.20/1M |
| Output Cost | $0.11/1M | $1.15/1M |
| Blended (3:1) | $0.05/1M | $0.44/1M |
| Specifications | ||
| Organization | Sarvam | StepFun |
| Release Date | Mar 6, 2026 | May 29, 2026 |
| Performance & Speed | ||
| Throughput | 216.7 tok/s | 371.9 tok/s |
| TTFT | 1167ms | 767ms |
| Latency | 10395ms | 6145ms |
| Composite Indices | ||
| Value Score | 100.0 | 18.7 |
| Reasoning Score | 27.5 | 47.8 |
| Intelligence | 12.3 | 42.6 |
| Coding | 7.9 | 37.1 |
| Standard Benchmarks | ||
| GPQA | 63.3% | 80.9% |
| HLE | 7.0% | 19.9% |
| SciCode | 19.2% | 40.0% |
| LCR | 0.0% | 63.7% |
| IFBench | 26.5% | 67.3% |
| TAU-bench v2 | 34.5% | 98.5% |
| TerminalBench Hard | 2.3% | 35.6% |
Key Takeaways
30B (high) offers the best value at $0.03/1M, making it ideal for high-volume applications and cost-conscious projects.
Step 3.7 Flash has the strongest reasoning profile with a 47.8 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
30B (high)
- Cost-sensitive applications
- High-volume processing
Step 3.7 Flash
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
