DeepSeek V3.2 vs Step 3.7 Flash
Updated October 21, 2026. 16 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; Step 3.7 Flash has none, so the two cannot be ranked on coding.
Step 3.7 Flash has the edge where the context window is larger, 262K against 164K tokens, and where what matters is τ²-Bench Telecom or Design Arena: websites, where it leads.
- Shared results
- 16
- DeepSeek V3.2 only
- 59
- Step 3.7 Flash only
- 2
- Like-for-like categories
- 6 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only DeepSeek V3.2 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
DeepSeek V3.2
DeepSeek V3.2 leads, 21.5 against 19.5.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only DeepSeek V3.2 has a GPQA Diamond result, 80.3%.
Directional only
Math
AIME
No call
Only DeepSeek V3.2 has a AIME result, 84.6%.
Directional only
Knowledge
MMLU Pro
No call
Only DeepSeek V3.2 has a MMLU Pro result, 84.9%.
Directional only
Web design
Design Arena: websites
Step 3.7 Flash
Step 3.7 Flash leads, 1196 against 1175.
Same board, both measured
Long documents
Listed context window
Step 3.7 Flash
Step 3.7 Flash takes 262K tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3.2
DeepSeek V3.2 $0.0007, Step 3.7 Flash $0.0008 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only DeepSeek V3.2 has the number, $0.99.
Directional only
At a glance
- Coding index
- DeepSeek V3.2 30.0 from 3 benchmarks, Step 3.7 Flash not benchmarked.
- Widest category
- Agentic work, 7.9 points apart on average over 1 shared benchmark.
- Widest single gap
- Design Arena: ASCII art: DeepSeek V3.2 1082 against Step 3.7 Flash 1152, 8.7 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.2 $0.88 against Step 3.7 Flash $1.15 per million output tokens, 1.3x apart.
- Context window
- DeepSeek V3.2 takes 164K tokens, Step 3.7 Flash 262K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | DeepSeek V3.2 | Bars | Step 3.7 Flash | Ties |
|---|---|---|---|---|
| Coding | 1 | 0 | 1 tie | |
| Intelligence | 1 | 0 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 2 | 0 | ||
| Web design | 1 | 7 | ||
| General | 0 | 2 | ||
| All shared boards | 5 | 10 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index10
| Benchmark | DeepSeek V3.2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| SWE-bench Verified | 70.0% | Not measured | Only DeepSeek V3.2 measured |
| SWE-bench Multilingual | 59.0% | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev | 1362 | Not measured | Only DeepSeek V3.2 measured |
| AA Coding Index | 44.2 | 39.6 | DeepSeek V3.2 |
| LiveCodeBench (Vals AI) | 80.7% | Not measured | Only DeepSeek V3.2 measured |
| SWE-bench Verified (Vals AI) | 67.6% | Not measured | Only DeepSeek V3.2 measured |
| Vibe Code Bench (Vals AI) | 5.1% | Not measured | Only DeepSeek V3.2 measured |
| LiveCodeBench (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| SciCode | Not measured | 43.9% | Only Step 3.7 Flash measured |
| Terminal-Bench Hard (Artificial Analysis run) | 35.6% | 35.6% | Tie |
| Terminal-Bench | 39.6% | Not measured | Only DeepSeek V3.2 measured |
| ALE-Bench | Not measured | 694.1 | Only Step 3.7 Flash measured |
| LMArena Text: coding | 1453 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: software and IT | 1449 | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev: React | 1350 | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev: HTML | 1371 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 22 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V3.2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 21.5 | 19.5 | DeepSeek V3.2 |
| Epoch Capabilities Index | 146.1 | Not measured | Only DeepSeek V3.2 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 90.6% | 98.5% | Step 3.7 Flash |
| APEX-Agents | 21.3% | Not measured | Only DeepSeek V3.2 measured |
| Vending-Bench 2 | $1,034 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 36 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | DeepSeek V3.2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| GPQA Diamond | 80.3% | Not measured | Only DeepSeek V3.2 measured |
| GPQA Diamond (Artificial Analysis run) | 84.0% | 80.9% | DeepSeek V3.2 |
| Humanity's Last Exam (Artificial Analysis run) | 24.6% | 21.4% | DeepSeek V3.2 |
| ARC-AGI | 57.0% | Not measured | Only DeepSeek V3.2 measured |
| ARC-AGI-2 | 4.0% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: hard prompts | 1434 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: expert | 1436 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: hard prompts in English | 1446 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 13 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | DeepSeek V3.2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| AIME | 84.6% | Not measured | Only DeepSeek V3.2 measured |
| MGSM (Vals AI) | 86.0% | Not measured | Only DeepSeek V3.2 measured |
| AA Math Index | 92.0 | Not measured | Only DeepSeek V3.2 measured |
| AIME 2025 (Artificial Analysis run) | 92.0% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: math | 1435 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: mathematical work | 1440 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | DeepSeek V3.2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| MMLU Pro | 84.9% | Not measured | Only DeepSeek V3.2 measured |
| LegalBench (Vals AI) | 76.1% | Not measured | Only DeepSeek V3.2 measured |
| CaseLaw (Vals AI) | 55.4% | Not measured | Only DeepSeek V3.2 measured |
| CorpFin (Vals AI) | 51.0% | Not measured | Only DeepSeek V3.2 measured |
| TaxEval (Vals AI) | 68.2% | Not measured | Only DeepSeek V3.2 measured |
| MedQA (Vals AI) | 93.9% | Not measured | Only DeepSeek V3.2 measured |
| MMLU Pro (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: science | 1446 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: medicine and healthcare | 1440 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: legal and government | 1425 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: business and finance | 1410 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index17
| Benchmark | DeepSeek V3.2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| Design Arena: websites | 1175 | 1196 | Step 3.7 Flash |
| Design Arena: UI components | 1149 | 1179 | Step 3.7 Flash |
| Design Arena: game dev | 1131 | 1158 | Step 3.7 Flash |
| Design Arena: data viz | 1158 | 1172 | Step 3.7 Flash |
| Design Arena: 3D | 1133 | 1129 | DeepSeek V3.2 |
| Design Arena: all code categories | 1164 | 1182 | Step 3.7 Flash |
| Design Arena: SVG | 1032 | 1085 | Step 3.7 Flash |
| Design Arena: ASCII art | 1082 | 1152 | Step 3.7 Flash |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V3.2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| IFBench | 60.7% | 67.3% | Step 3.7 Flash |
| Long context reasoning (AA-LCR) | 73.3% | 73.7% | Step 3.7 Flash |
| DTBench | 85.6% | Not measured | Only DeepSeek V3.2 measured |
| LMCA | 28.8% | Not measured | Only DeepSeek V3.2 measured |
| CL-bench | 12.4% | Not measured | Only DeepSeek V3.2 measured |
| CL-bench Life | 7.4% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text | 1425 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: instruction following | 1413 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: creative writing | 1400 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: English | 1439 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: non-English | 1409 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Chinese | 1455 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: German | 1413 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Japanese | 1374 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Korean | 1370 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: French | 1429 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Spanish | 1424 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Russian | 1424 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Polish | 1419 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: multi-turn | 1427 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: longer queries | 1428 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: writing and language | 1407 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: entertainment and media | 1395 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3.2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
DeepSeek V3.2 costs less
Repository review
50K input + 3K output tokens
Step 3.7 Flash costs less
Agent loop
200K input + 10K output tokens
Step 3.7 Flash costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | DeepSeek V3.2 | StepFun Step 3.7 Flash |
|---|---|---|
| Maker | DeepSeek | StepFun |
| Weights | Open weights | Open weights |
| Released | December 1, 2025 | May 28, 2026 |
| Context window | 164K | 262K |
| Input $/Mtok | $0.29 | $0.20 |
| Output $/Mtok | $0.88 | $1.15 |
| Coding index | 30.0 | Not benchmarked |
| Independent measurements behind it | 3 | 0 |
| Cost per solved task | $0.99 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.2 better than Step 3.7 Flash for coding?
Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; Step 3.7 Flash has none, so the two cannot be ranked on coding. Step 3.7 Flash has the edge where the context window is larger, 262K against 164K tokens, and where what matters is τ²-Bench Telecom or Design Arena: websites, where it leads.
Which is cheaper, DeepSeek V3.2 or Step 3.7 Flash?
DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; Step 3.7 Flash costs $0.20 and $1.15. Cost per solved task is known for DeepSeek V3.2 only.
Which has the bigger context window, DeepSeek V3.2 or Step 3.7 Flash?
Step 3.7 Flash, with 262K tokens against 164K.
How many benchmarks is the DeepSeek V3.2 vs Step 3.7 Flash comparison based on?
16 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.2's coding index rests on 3 independent benchmarks and Step 3.7 Flash's on 0. Where only one model has a result, the page says so instead of naming a winner.