Qwen3.5-35B-A3B vs Step 3.5 Flash
Qwen3.5-35B-A3B leads Step 3.5 Flash on the Artificial Analysis Intelligence Index, 19.3 to 17.0, and Step 3.5 Flash costs 4.3x less per output token ($0.30 vs $1.30 per million). Updated October 22, 2026; 35 benchmarks have a result for both.
Qwen3.5-35B-A3B or Step 3.5 Flash: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Qwen3.5-35B-A3B for work measured by Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.
- Shared results
- 35
- Qwen3.5-35B-A3B only
- 10
- Step 3.5 Flash only
- 0
- Like-for-like categories
- 7 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
Qwen3.5-35B-A3B
Qwen3.5-35B-A3B leads, 19.3 against 17.0.
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 3.5 Flash
Qwen3.5-35B-A3B $0.0008, Step 3.5 Flash $0.0003 per turn.
List prices
At a glance
- Coding index
- Qwen3.5-35B-A3B not benchmarked, Step 3.5 Flash not benchmarked.
- Widest category
- Agentic work, 5.3 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): Qwen3.5-35B-A3B 72.0% against Step 3.5 Flash 63.0%, 9.0 points apart on a 0 to 100 scale.
- Output price
- Qwen3.5-35B-A3B $1.30 against Step 3.5 Flash $0.30 per million output tokens, 4.3x 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 | Qwen3.5-35B-A3B | Bars | Step 3.5 Flash | Ties |
|---|---|---|---|---|
| Coding | 0 | 3 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 1 | 4 | ||
| Math | 0 | 2 | ||
| Knowledge | 1 | 3 | ||
| General | 4 | 15 | ||
| All shared boards | 7 | 28 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
| Benchmark | Qwen3.5-35B-A3B | Step 3.5 Flash | Leader |
|---|---|---|---|
| LMArena WebDev | 1254 | Not measured | Only Qwen3.5-35B-A3B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 26.5% | 32.6% | Step 3.5 Flash |
| ALE-Bench | 221.8 | Not measured | Only Qwen3.5-35B-A3B measured |
| LMArena Text: coding | 1410 | 1436 | Step 3.5 Flash |
| LMArena Text: software and IT | 1415 | 1434 | Step 3.5 Flash |
| LMArena WebDev: React | 1238 | Not measured | Only Qwen3.5-35B-A3B measured |
| LMArena WebDev: HTML | 1301 | Not measured | Only Qwen3.5-35B-A3B measured |
| Neither model has a result on the other 32 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Qwen3.5-35B-A3B | Step 3.5 Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 19.3 | 17.0 | Qwen3.5-35B-A3B |
| Epoch Capabilities Index | 142.5 | Not measured | Only Qwen3.5-35B-A3B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3.5-35B-A3B | Step 3.5 Flash | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 89.2% | 94.4% | Step 3.5 Flash |
| Vending-Bench 2 | $463 | Not measured | Only Qwen3.5-35B-A3B measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index14
| Benchmark | Qwen3.5-35B-A3B | Step 3.5 Flash | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 84.5% | 83.1% | Qwen3.5-35B-A3B |
| Humanity's Last Exam (Artificial Analysis run) | 21.0% | 24.5% | Step 3.5 Flash |
| GPQA Diamond (Epoch AI run) | 83.5% | Not measured | Only Qwen3.5-35B-A3B measured |
| LMArena Text: hard prompts | 1400 | 1411 | Step 3.5 Flash |
| LMArena Text: expert | 1408 | 1421 | Step 3.5 Flash |
| LMArena Text: hard prompts in English | 1411 | 1421 | Step 3.5 Flash |
| Neither model has a result on the other 16 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Qwen3.5-35B-A3B | Step 3.5 Flash | Leader |
|---|---|---|---|
| OTIS Mock AIME | 70.0% | Not measured | Only Qwen3.5-35B-A3B measured |
| LMArena Text: math | 1404 | 1408 | Step 3.5 Flash |
| LMArena Text: mathematical work | 1410 | 1421 | Step 3.5 Flash |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | Qwen3.5-35B-A3B | Step 3.5 Flash | Leader |
|---|---|---|---|
| LMArena Text: science | 1413 | 1415 | Step 3.5 Flash |
| LMArena Text: medicine and healthcare | 1421 | 1408 | Qwen3.5-35B-A3B |
| LMArena Text: legal and government | 1399 | 1408 | Step 3.5 Flash |
| LMArena Text: business and finance | 1394 | 1394 | Step 3.5 Flash |
| Neither model has a result on the other 14 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.5-35B-A3B | Step 3.5 Flash | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index415
| Benchmark | Qwen3.5-35B-A3B | Step 3.5 Flash | Leader |
|---|---|---|---|
| IFBench | 72.5% | 66.5% | Qwen3.5-35B-A3B |
| Long context reasoning (AA-LCR) | 72.0% | 63.0% | Qwen3.5-35B-A3B |
| DTBench | 80.0% | Not measured | Only Qwen3.5-35B-A3B measured |
| LMCA | 29.5% | Not measured | Only Qwen3.5-35B-A3B measured |
| LMArena Text | 1395 | 1403 | Step 3.5 Flash |
| LMArena Text: instruction following | 1379 | 1385 | Step 3.5 Flash |
| LMArena Text: creative writing | 1347 | 1357 | Step 3.5 Flash |
| LMArena Text: English | 1407 | 1417 | Step 3.5 Flash |
| LMArena Text: non-English | 1378 | 1385 | Step 3.5 Flash |
| LMArena Text: Chinese | 1457 | 1446 | Qwen3.5-35B-A3B |
| LMArena Text: German | 1367 | 1405 | Step 3.5 Flash |
| LMArena Text: Japanese | 1326 | 1353 | Step 3.5 Flash |
| LMArena Text: Korean | 1355 | 1351 | Qwen3.5-35B-A3B |
| LMArena Text: French | 1412 | 1421 | Step 3.5 Flash |
| LMArena Text: Spanish | 1390 | 1419 | Step 3.5 Flash |
| LMArena Text: Russian | 1376 | 1385 | Step 3.5 Flash |
| LMArena Text: Polish | 1385 | 1389 | Step 3.5 Flash |
| LMArena Text: multi-turn | 1390 | 1404 | Step 3.5 Flash |
| LMArena Text: longer queries | 1389 | 1402 | Step 3.5 Flash |
| LMArena Text: writing and language | 1365 | 1372 | Step 3.5 Flash |
| LMArena Text: entertainment and media | 1347 | 1360 | Step 3.5 Flash |
| Neither model has a result on the other 25 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.5-35B-A3B | Step 3.5 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 3.5 Flash costs less
Repository review
50K input + 3K output tokens
Step 3.5 Flash costs less
Agent loop
200K input + 10K output tokens
Step 3.5 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 | Qwen3.5-35B-A3B | StepFun Step 3.5 Flash |
|---|---|---|
| Maker | Qwen | StepFun |
| Weights | Open weights | Open weights |
| Released | February 25, 2026 | January 29, 2026 |
| Context window | 262K | 262K |
| Input $/Mtok | $0.1625 | $0.10 |
| Output $/Mtok | $1.30 | $0.30 |
| 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 Qwen3.5-35B-A3B better than Step 3.5 Flash for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen3.5-35B-A3B for work measured by Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.
Which is cheaper, Qwen3.5-35B-A3B or Step 3.5 Flash?
Qwen3.5-35B-A3B costs $0.1625 per million input tokens and $1.30 per million output tokens; Step 3.5 Flash costs $0.10 and $0.30. Cost per solved task is known for neither of them.
Which has the bigger context window, Qwen3.5-35B-A3B or Step 3.5 Flash?
Neither: both take 262K tokens.
How many benchmarks is the Qwen3.5-35B-A3B vs Step 3.5 Flash comparison based on?
35 benchmarks have a result for both models as of October 22, 2026. Qwen3.5-35B-A3B's coding index rests on 1 independent benchmark and Step 3.5 Flash's on 0. Where only one model has a result, the page says so instead of naming a winner.