MoonshotAI: Kimi K2.7 Code vs StepFun: Step 3.7 Flash
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| MoonshotAI: Kimi K2.7 Code | StepFun: Step 3.7 Flash | |
|---|---|---|
| Vendor | moonshotai | stepfun |
| Quality Score | 100 | 100 |
| Benchmark Score | 74.1 | 50.8 |
| Input Price | $0.60/M | $0.20/M |
| Output Price | $3.50/M | $1.15/M |
| Context Window | 262,144 | 262,144 |
| Max Output | 235,929 | 230,400 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | 69.2 | 49.9 |
| ai_index_agentic | 48.8 | 35.5 |
| ai_index_coding | 100.0 | 65.3 |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Step 3.7 Flash costs $0.49 and Kimi K2.7 Code costs $1.48, so Step 3.7 Flash is about 3.0 times cheaper for the same work.
Both read up to 262,144 tokens at once, roughly 393 pages of text.
Only Step 3.7 Flash offers video input.
On our blended benchmark score Kimi K2.7 Code leads 74.1 to 50.8.
Across the 20 tasks where they differ, Kimi K2.7 Code scores higher on 19 (SQL Generation, Code Review, Code Refactoring and others), Step 3.7 Flash on 1 (Code Completion).
Kimi K2.7 Code was released in June 2026 and Step 3.7 Flash in May 2026.
Pick Kimi K2.7 Code if you need benchmark performance or the stronger all-round task scores; pick Step 3.7 Flash if you need lower cost or video input.
Costs use current list prices per million tokens; page counts assume about 0.75 words per token and 500 words per page.
Who wins by task?
| Task | MoonshotAI: Kimi K2.7 Code | StepFun: Step 3.7 Flash |
|---|---|---|
| SQL Generation | 163 | 153 |
| Code Review | 155 | 146 |
| Code Completion | 129 | 130 |
| Code Refactoring | 151 | 144 |
| Bug Fixing | 165 | 155 |
| Unit Test Generation | 147 | 139 |
| Code Documentation | 135 | 133 |
| Regex Writing | 133 | 129 |
| CI/CD Pipelines | 138 | 131 |
| Frontend Component Design | 142 | 136 |
| Data Analysis | 162 | 150 |
| CSV / Spreadsheet Cleanup | 147 | 141 |
| ETL Scripting | 144 | 137 |
| JSON Extraction | 147 | 142 |
| Bulk Data Labeling | 134 | 133 |
| OCR / Document Parsing | 142 | 138 |
| Table Extraction from PDFs | 142 | 138 |
| Long-Document Summarization | 147 | 142 |
| Short-Form Summarization | 130 | 128 |
| Blog Post Writing | 134 | 129 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →