Enter opens the highlighted result. Esc closes.

Qwen3.7 Plus vs Step 3.5 Flash

Updated October 21, 2026. 35 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Qwen3.7 Plus Replace Step 3.5 Flash
Qwen3.7 PlusQwen
Coding
33.2
Overall
25.2
Output $/M
$1.28
34
Step 3.5 FlashStepFun
Coding
No data
Overall
17.0
Output $/M
$0.30
1
vs boards won of 35 shared

Decision reading

Only Qwen3.7 Plus has a coding score, 33.2 on the Vibe Coding Index; Step 3.5 Flash has none, so the two cannot be ranked on coding.

Step 3.5 Flash has the edge where output tokens cost 4.3x less, and where the benchmark that matters is τ²-Bench Telecom, where it leads.

Model AQwen3.7 PlusQwen33.2/1002 independent benchmarksNo cost per solved taskModel BStep 3.5 FlashStepFunNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
35
Qwen3.7 Plus only
40
Step 3.5 Flash only
0
Like-for-like categories
7 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.

At a glance

Coding index
Qwen3.7 Plus 33.2 from 2 benchmarks, Step 3.5 Flash not benchmarked.
Widest category
General, 9.8 points apart on average over 19 shared benchmarks.
Widest single gap
Terminal-Bench Hard (Artificial Analysis run): Qwen3.7 Plus 47.0% against Step 3.5 Flash 32.6%, 14.4 points apart on a 0 to 100 scale.
Output price
Qwen3.7 Plus $1.28 against Step 3.5 Flash $0.30 per million output tokens, 4.3x apart.
Context window
Qwen3.7 Plus takes 1M tokens, Step 3.5 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.

Boards won, where both have a result
CategoryQwen3.7 PlusBarsStep 3.5 FlashTies
Coding30
Intelligence10
Agentic work01
Reasoning50
Math20
Knowledge40
General190
All shared boards341
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for Qwen3.7 Plus and Step 3.5 Flash
BenchmarkQwen3.7 PlusStep 3.5 FlashLeader
AA Coding Index55.9Not measuredOnly Qwen3.7 Plus measured
Vibe Code Bench (Vals AI)46.4%Not measuredOnly Qwen3.7 Plus measured
Code migration (Vals AI)12.9%Not measuredOnly Qwen3.7 Plus measured
Terminal-Bench 2.1 (Vals AI)52.8%Not measuredOnly Qwen3.7 Plus measured
SkillsBench (Vals AI)54.3%Not measuredOnly Qwen3.7 Plus measured
SciCode46.1%Not measuredOnly Qwen3.7 Plus measured
Terminal-Bench Hard (Artificial Analysis run)47.0%32.6%Qwen3.7 Plus
FrontierCode10.2%Not measuredOnly Qwen3.7 Plus measured
LMArena Text: coding14731436Qwen3.7 Plus
LMArena Text: software and IT14731434Qwen3.7 Plus
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Qwen3.7 Plus and Step 3.5 Flash
BenchmarkQwen3.7 PlusStep 3.5 FlashLeader
AA Intelligence Index25.217.0Qwen3.7 Plus
Epoch Capabilities Index147.0Not measuredOnly Qwen3.7 Plus measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Qwen3.7 Plus and Step 3.5 Flash
BenchmarkQwen3.7 PlusStep 3.5 FlashLeader
AA Agentic Index17.5Not measuredOnly Qwen3.7 Plus measured
Finance Agent (Vals AI)38.2%Not measuredOnly Qwen3.7 Plus measured
Tax Agent Bench (Vals AI)10.5%Not measuredOnly Qwen3.7 Plus measured
Legal Research Bench (Vals AI)16.4%Not measuredOnly Qwen3.7 Plus measured
Excel Modeling Benchmark (Vals AI)49.3%Not measuredOnly Qwen3.7 Plus measured
τ²-Bench Telecom93.0%94.4%Step 3.5 Flash
OSWorld 2.02.8%Not measuredOnly Qwen3.7 Plus measured
Neither model has a result on the other 32 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for Qwen3.7 Plus and Step 3.5 Flash
BenchmarkQwen3.7 PlusStep 3.5 FlashLeader
GPQA Diamond (Artificial Analysis run)90.0%83.1%Qwen3.7 Plus
Humanity's Last Exam (Artificial Analysis run)35.6%24.5%Qwen3.7 Plus
GPQA Diamond (Epoch AI run)87.9%Not measuredOnly Qwen3.7 Plus measured
Mystery game puzzles17.0%Not measuredOnly Qwen3.7 Plus measured
LMArena Text: hard prompts14601411Qwen3.7 Plus
LMArena Text: expert14661421Qwen3.7 Plus
LMArena Text: hard prompts in English14601421Qwen3.7 Plus
LMArena Vision: diagrams1292Not measuredOnly Qwen3.7 Plus measured
LMArena Vision: homework1295Not measuredOnly Qwen3.7 Plus measured
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Qwen3.7 Plus and Step 3.5 Flash
BenchmarkQwen3.7 PlusStep 3.5 FlashLeader
OTIS Mock AIME93.3%Not measuredOnly Qwen3.7 Plus measured
FrontierMath, tiers 1 to 334.4%Not measuredOnly Qwen3.7 Plus measured
LMArena Text: math14671408Qwen3.7 Plus
LMArena Text: mathematical work14701421Qwen3.7 Plus
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for Qwen3.7 Plus and Step 3.5 Flash
BenchmarkQwen3.7 PlusStep 3.5 FlashLeader
MortgageTax (Vals AI)66.2%Not measuredOnly Qwen3.7 Plus measured
LMArena Text: science14641415Qwen3.7 Plus
LMArena Text: medicine and healthcare14641408Qwen3.7 Plus
LMArena Text: legal and government14511408Qwen3.7 Plus
LMArena Text: business and finance14351394Qwen3.7 Plus
Neither model has a result on the other 12 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for Qwen3.7 Plus and Step 3.5 Flash
BenchmarkQwen3.7 PlusStep 3.5 FlashLeader
Design Arena: websites1269Not measuredOnly Qwen3.7 Plus measured
Design Arena: UI components1261Not measuredOnly Qwen3.7 Plus measured
Design Arena: game dev1262Not measuredOnly Qwen3.7 Plus measured
Design Arena: data viz1275Not measuredOnly Qwen3.7 Plus measured
Design Arena: 3D1239Not measuredOnly Qwen3.7 Plus measured
Design Arena: all code categories1269Not measuredOnly Qwen3.7 Plus measured
Design Arena: SVG1208Not measuredOnly Qwen3.7 Plus measured
Design Arena: ASCII art1144Not measuredOnly Qwen3.7 Plus measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index190
General benchmarks for Qwen3.7 Plus and Step 3.5 Flash
BenchmarkQwen3.7 PlusStep 3.5 FlashLeader
SAGE (Vals AI)39.3%Not measuredOnly Qwen3.7 Plus measured
Vals Multimodal Index53.9%Not measuredOnly Qwen3.7 Plus measured
IFBench78.0%66.5%Qwen3.7 Plus
Long context reasoning (AA-LCR)73.0%63.0%Qwen3.7 Plus
DTBench84.0%Not measuredOnly Qwen3.7 Plus measured
LMCA37.6%Not measuredOnly Qwen3.7 Plus measured
LMArena Text14541403Qwen3.7 Plus
LMArena Text: instruction following14391385Qwen3.7 Plus
LMArena Text: creative writing14381357Qwen3.7 Plus
LMArena Vision1278Not measuredOnly Qwen3.7 Plus measured
LMArena Text: English14581417Qwen3.7 Plus
LMArena Text: non-English14451385Qwen3.7 Plus
LMArena Text: Chinese15091446Qwen3.7 Plus
LMArena Text: German14711405Qwen3.7 Plus
LMArena Text: Japanese14121353Qwen3.7 Plus
LMArena Text: Korean14131351Qwen3.7 Plus
LMArena Text: French14721421Qwen3.7 Plus
LMArena Text: Spanish14571419Qwen3.7 Plus
LMArena Text: Russian14571385Qwen3.7 Plus
LMArena Text: Polish14491389Qwen3.7 Plus
LMArena Text: multi-turn14591404Qwen3.7 Plus
LMArena Text: longer queries14541402Qwen3.7 Plus
LMArena Text: writing and language14371372Qwen3.7 Plus
LMArena Text: entertainment and media14221360Qwen3.7 Plus
LMArena Vision: English1280Not measuredOnly Qwen3.7 Plus measured
LMArena Vision: Chinese1332Not measuredOnly Qwen3.7 Plus measured
LMArena Vision: reading text1288Not measuredOnly Qwen3.7 Plus measured
LMArena Vision: humor1261Not measuredOnly Qwen3.7 Plus measured
LMArena Vision: creative writing1258Not measuredOnly Qwen3.7 Plus measured
LMArena Document1444Not measuredOnly Qwen3.7 Plus measured
Neither model has a result on the other 16 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Qwen3.7 Plus and Step 3.5 Flash
BenchmarkQwen3.7 PlusStep 3.5 FlashLeader
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

Qwen3.7 Plus$0.0010Fits in one request
Step 3.5 Flash$0.0003Fits in one request

Step 3.5 Flash costs less

Repository review

50K input + 3K output tokens

Qwen3.7 Plus$0.020Fits in one request
Step 3.5 Flash$0.0059Fits in one request

Step 3.5 Flash costs less

Agent loop

200K input + 10K output tokens

Qwen3.7 Plus$0.077Fits in one request
Step 3.5 Flash$0.023Fits in one request

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.

Specifications of Qwen3.7 Plus and Step 3.5 Flash
SpecificationQwen3.7 PlusStepFun Step 3.5 Flash
MakerQwenStepFun
WeightsNo public weights listedOpen weights
ReleasedJune 3, 2026January 29, 2026
Context window1M262K
Input $/Mtok$0.32$0.10
Output $/Mtok$1.28$0.30
Coding index33.2Not benchmarked
Independent measurements behind it20
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Qwen3.7 Plus better than Step 3.5 Flash for coding?

Only Qwen3.7 Plus has a coding score, 33.2 on the Vibe Coding Index; Step 3.5 Flash has none, so the two cannot be ranked on coding. Step 3.5 Flash has the edge where output tokens cost 4.3x less, and where the benchmark that matters is τ²-Bench Telecom, where it leads.

Which is cheaper, Qwen3.7 Plus or Step 3.5 Flash?

Qwen3.7 Plus costs $0.32 per million input tokens and $1.28 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, Qwen3.7 Plus or Step 3.5 Flash?

Qwen3.7 Plus, with 1M tokens against 262K.

How many benchmarks is the Qwen3.7 Plus vs Step 3.5 Flash comparison based on?

35 benchmarks have a result for both models as of October 21, 2026. Qwen3.7 Plus's coding index rests on 2 independent benchmarks and Step 3.5 Flash's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next