Model Comparison
Step 3.7 Flash
vs. Llama 3.1 Tulu3 405B
Comparing 2 AI models · 11 benchmarks · StepFun, Allen Institute for AI
Recommended Pick
St Step 3.7 Flash 6 metric wins Strongest on: Throughput, Reasoning, Intelligence
Lowest Price
Llama 3.1 Tulu3 405B
$0.00/1M 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
Price gap
Llama 3.1 Tulu3 405B is ∞x cheaper on input tokens than Step 3.7 Flash.
Reasoning gap
Step 3.7 Flash leads Llama 3.1 Tulu3 405B by 15.7 points on reasoning.
Top-pick rationale
Step 3.7 Flash wins 6 measurable categories, including Throughput, Reasoning, Intelligence, GPQA.
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
—
Llama 3.1 Tulu3 405B
Allen Institute for AI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick St Step 3.7 Flash | Al Llama 3.1 Tulu3 405B |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.20/1M | $0.00/1M |
| Output Cost | $1.15/1M | $0.00/1M |
| Blended (3:1) | $0.44/1M | — |
| Specifications | ||
| Organization | StepFun | Allen Institute for AI |
| Release Date | May 29, 2026 | Jan 30, 2025 |
| Performance & Speed | ||
| Throughput | 376.9 tok/s | — |
| TTFT | 767ms | — |
| Latency | 6073ms | — |
| Composite Indices | ||
| Value Score | 100.0 | — |
| Reasoning Score | 47.8 | 32.1 |
| Intelligence | 42.6 | 14.1 |
| Coding | 37.1 | — |
| Standard Benchmarks | ||
| GPQA | 80.9% | 51.6% |
| MMLU Pro | — | 71.6% |
| HLE | 19.9% | 3.5% |
| LiveCodeBench | — | 29.1% |
| MATH 500 | — | 77.8% |
| AIME (Original) | — | 13.3% |
| SciCode | 40.0% | 30.2% |
| LCR | 63.7% | — |
| IFBench | 67.3% | — |
| TAU-bench v2 | 98.5% | — |
| TerminalBench Hard | 35.6% | — |
Key Takeaways
Llama 3.1 Tulu3 405B offers the best value at $0.00/1M, 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
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
Llama 3.1 Tulu3 405B
- Cost-sensitive applications
- High-volume processing
