Qwen3.5 397B A17B vs Step 3.7 Flash
Qwen3.5 397B A17B leads Step 3.7 Flash on the Artificial Analysis Intelligence Index, 21.4 to 19.5, and Step 3.7 Flash costs 2.0x less per output token ($1.15 vs $2.34 per million). Updated October 22, 2026; 16 benchmarks have a result for both.
Qwen3.5 397B A17B or Step 3.7 Flash: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Qwen3.5 397B A17B for work measured by ALE-Bench or τ²-Bench Telecom, where it leads.
- Shared results
- 16
- Qwen3.5 397B A17B only
- 49
- Step 3.7 Flash only
- 2
- Like-for-like categories
- 6 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
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
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Qwen3.5 397B A17B
Qwen3.5 397B A17B leads, 21.4 against 19.5.
Same board, both measured
Web design
Design Arena: websites
Step 3.7 Flash
Step 3.7 Flash leads, 1196 against 1190.
Same board, both measured
Long documents
Listed context window
No call
Both take 262K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Step 3.7 Flash
Qwen3.5 397B A17B $0.0016, Step 3.7 Flash $0.0008 per turn.
List prices
At a glance
- Coding index
- Qwen3.5 397B A17B not benchmarked, Step 3.7 Flash not benchmarked.
- Widest category
- Reasoning, 8.0 points apart on average over 2 shared benchmarks.
- Widest single gap
- IFBench: Qwen3.5 397B A17B 78.8% against Step 3.7 Flash 67.3%, 11.5 points apart on a 0 to 100 scale.
- Output price
- Qwen3.5 397B A17B $2.34 against Step 3.7 Flash $1.15 per million output tokens, 2.0x apart.
- Context window
- Both take 262K tokens.
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 | Qwen3.5 397B A17B | Bars | Step 3.7 Flash | Ties |
|---|---|---|---|---|
| Coding | 2 | 1 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 2 | 0 | ||
| Web design | 3 | 4 | ||
| General | 2 | 0 | ||
| All shared boards | 10 | 6 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index21
| Benchmark | Qwen3.5 397B A17B | Step 3.7 Flash | Leader |
|---|---|---|---|
| LMArena WebDev | 1400 | Not measured | Only Qwen3.5 397B A17B measured |
| AA Coding Index | Not measured | 39.6 | Only Step 3.7 Flash measured |
| SciCode | 44.8% | 43.9% | Qwen3.5 397B A17B |
| Terminal-Bench Hard (Artificial Analysis run) | 40.9% | 35.6% | Qwen3.5 397B A17B |
| ALE-Bench | 621.9 | 694.1 | Step 3.7 Flash |
| LMArena Text: coding | 1464 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: software and IT | 1463 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena WebDev: React | 1388 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena WebDev: HTML | 1410 | Not measured | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 30 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Qwen3.5 397B A17B | Step 3.7 Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 21.4 | 19.5 | Qwen3.5 397B A17B |
| Epoch Capabilities Index | 146.8 | Not measured | Only Qwen3.5 397B A17B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3.5 397B A17B | Step 3.7 Flash | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 95.6% | 98.5% | Step 3.7 Flash |
| APEX-Agents | 24.9% | Not measured | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Qwen3.5 397B A17B | Step 3.7 Flash | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 89.3% | 80.9% | Qwen3.5 397B A17B |
| Humanity's Last Exam (Artificial Analysis run) | 29.0% | 21.4% | Qwen3.5 397B A17B |
| GPQA Diamond (Epoch AI run) | 86.4% | Not measured | Only Qwen3.5 397B A17B measured |
| Mystery game puzzles | 18.0% | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: hard prompts | 1448 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: expert | 1462 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: hard prompts in English | 1450 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: diagrams | 1277 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: homework | 1292 | Not measured | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 13 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Qwen3.5 397B A17B | Step 3.7 Flash | Leader |
|---|---|---|---|
| OTIS Mock AIME | 88.9% | Not measured | Only Qwen3.5 397B A17B measured |
| FrontierMath, tiers 1 to 3 | 31.2% | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: math | 1453 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: mathematical work | 1454 | Not measured | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Qwen3.5 397B A17B | Step 3.7 Flash | Leader |
|---|---|---|---|
| LMArena Text: science | 1457 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: medicine and healthcare | 1455 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: legal and government | 1441 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: business and finance | 1435 | Not measured | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 14 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index34
| Benchmark | Qwen3.5 397B A17B | Step 3.7 Flash | Leader |
|---|---|---|---|
| Design Arena: websites | 1190 | 1196 | Step 3.7 Flash |
| Design Arena: UI components | 1160 | 1177 | Step 3.7 Flash |
| Design Arena: game dev | 1140 | 1158 | Step 3.7 Flash |
| Design Arena: data viz | 1175 | 1173 | Qwen3.5 397B A17B |
| Design Arena: 3D | 1160 | 1129 | Qwen3.5 397B A17B |
| Design Arena: all code categories | 1179 | 1182 | Step 3.7 Flash |
| Design Arena: SVG | 1139 | 1084 | Qwen3.5 397B A17B |
| Design Arena: ASCII art | Not measured | 1152 | Only Step 3.7 Flash measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Qwen3.5 397B A17B | Step 3.7 Flash | Leader |
|---|---|---|---|
| IFBench | 78.8% | 67.3% | Qwen3.5 397B A17B |
| Long context reasoning (AA-LCR) | 77.3% | 73.7% | Qwen3.5 397B A17B |
| DTBench | 87.5% | Not measured | Only Qwen3.5 397B A17B measured |
| LMCA | 37.9% | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text | 1437 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: instruction following | 1424 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: creative writing | 1402 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision | 1262 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: English | 1443 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: non-English | 1430 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: Chinese | 1498 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: German | 1445 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: Japanese | 1429 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: Korean | 1384 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: French | 1462 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: Spanish | 1441 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: Russian | 1430 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: Polish | 1447 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: multi-turn | 1446 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: longer queries | 1441 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: writing and language | 1415 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Text: entertainment and media | 1399 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: English | 1268 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: Chinese | 1314 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: reading text | 1271 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: humor | 1262 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: captioning | 1230 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: recognizing things | 1265 | Not measured | Only Qwen3.5 397B A17B measured |
| LMArena Vision: creative writing | 1260 | Not measured | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 17 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.5 397B A17B | 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
Step 3.7 Flash 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 | Qwen3.5 397B A17B | StepFun Step 3.7 Flash |
|---|---|---|
| Maker | Qwen | StepFun |
| Weights | Open weights | Open weights |
| Released | February 16, 2026 | May 28, 2026 |
| Context window | 262K | 262K |
| Input $/Mtok | $0.39 | $0.20 |
| Output $/Mtok | $2.34 | $1.15 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3.5 397B A17B better than Step 3.7 Flash for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen3.5 397B A17B for work measured by ALE-Bench or τ²-Bench Telecom, where it leads.
Which is cheaper, Qwen3.5 397B A17B or Step 3.7 Flash?
Qwen3.5 397B A17B costs $0.39 per million input tokens and $2.34 per million output tokens; Step 3.7 Flash costs $0.20 and $1.15. Cost per solved task is known for neither of them.
Which has the bigger context window, Qwen3.5 397B A17B or Step 3.7 Flash?
Neither: both take 262K tokens.
How many benchmarks is the Qwen3.5 397B A17B vs Step 3.7 Flash comparison based on?
16 benchmarks have a result for both models as of October 22, 2026. Qwen3.5 397B A17B's coding index rests on 1 independent benchmark and Step 3.7 Flash's on 0. Where only one model has a result, the page says so instead of naming a winner.