Model Comparison
Step 3.7 Flash
vs. Trinity Large Thinking
Comparing 2 AI models · 7 benchmarks · StepFun, Arcee AI
Recommended Pick
St Step 3.7 Flash 15 metric wins Strongest on: Value, Input price, Throughput
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
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
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 1.2x cheaper on input tokens than Trinity Large Thinking.
Speed gap
Step 3.7 Flash generates about 2.0x as many tokens per second as Trinity Large Thinking.
Reasoning gap
Step 3.7 Flash leads Trinity Large Thinking by 7.2 points on reasoning.
Coding gap
Step 3.7 Flash leads Trinity Large Thinking by 9.9 points on coding.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Step 3.7 Flash
StepFun
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Trinity Large Thinking
Arcee AI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick St Step 3.7 Flash | Ar Trinity Large Thinking |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.20/1M | $0.23/1M |
| Output Cost | $1.15/1M | $0.88/1M |
| Blended (3:1) | $0.44/1M | $0.40/1M |
| Specifications | ||
| Organization | StepFun | Arcee AI |
| Release Date | May 29, 2026 | Apr 1, 2026 |
| Performance & Speed | ||
| Throughput | 365.0 tok/s | 183.4 tok/s |
| TTFT | 784ms | 818ms |
| Latency | 6263ms | 11720ms |
| Composite Indices | ||
| Value Score | 100.0 | 94.1 |
| Reasoning Score | 47.8 | 40.6 |
| Intelligence | 42.6 | 31.9 |
| Coding | 37.1 | 27.2 |
| Standard Benchmarks | ||
| GPQA | 80.9% | 75.2% |
| HLE | 19.9% | 14.7% |
| SciCode | 40.0% | 36.1% |
| LCR | 63.7% | 33.0% |
| IFBench | 67.3% | 56.3% |
| TAU-bench v2 | 98.5% | 90.1% |
| TerminalBench Hard | 35.6% | 22.7% |
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.
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
Step 3.7 Flash
- Cost-sensitive applications
- High-volume processing
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
Trinity Large Thinking
- General-purpose AI
- Versatile applications
