Enter opens the highlighted result. Esc closes.

Qwen2.5 72B Instruct vs Step 3.5 Flash

Step 3.5 Flash leads Qwen2.5 72B Instruct on the Artificial Analysis Intelligence Index, 17.0 to 7.7, and Step 3.5 Flash costs 1.3x less per output token ($0.30 vs $0.40 per million). Updated October 21, 2026; 33 benchmarks have a result for both.

Replace Qwen2.5 72B Instruct Replace Step 3.5 Flash
Qwen2.5 72B InstructQwen
Coding
No data
Overall
26.5
Output $/M
$0.40
0
Step 3.5 FlashStepFun
Coding
No data
Overall
No data
Output $/M
$0.30
33
vs boards won of 33 shared

Qwen2.5 72B Instruct or Step 3.5 Flash: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Qwen2.5 72B Instruct for work measured by Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.

Model AQwen2.5 72B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved taskModel BStep 3.5 FlashStepFunNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
33
Qwen2.5 72B Instruct only
20
Step 3.5 Flash only
2
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.

At a glance

Coding index
Qwen2.5 72B Instruct not benchmarked, Step 3.5 Flash not benchmarked.
Widest category
Agentic work, 59.9 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Qwen2.5 72B Instruct 34.5% against Step 3.5 Flash 94.4%, 59.9 points apart on a 0 to 100 scale.
Output price
Qwen2.5 72B Instruct $0.40 against Step 3.5 Flash $0.30 per million output tokens, 1.3x apart.
Context window
Qwen2.5 72B Instruct takes 33K 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
CategoryQwen2.5 72B InstructBarsStep 3.5 FlashTies
Coding03
Intelligence01
Agentic work01
Reasoning05
Math02
Knowledge04
General017
All shared boards033
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for Qwen2.5 72B Instruct and Step 3.5 Flash
BenchmarkQwen2.5 72B InstructStep 3.5 FlashLeader
LiveCodeBench (Artificial Analysis run)27.6%Not measuredOnly Qwen2.5 72B Instruct measured
Terminal-Bench Hard (Artificial Analysis run)4.5%32.6%Step 3.5 Flash
WeirdML16.0%Not measuredOnly Qwen2.5 72B Instruct measured
LMArena Text: coding12921436Step 3.5 Flash
LMArena Text: software and IT12921434Step 3.5 Flash
Neither model has a result on the other 34 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Qwen2.5 72B Instruct and Step 3.5 Flash
BenchmarkQwen2.5 72B InstructStep 3.5 FlashLeader
AA Intelligence Index7.717.0Step 3.5 Flash
Epoch Capabilities Index129.0Not measuredOnly Qwen2.5 72B Instruct measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Qwen2.5 72B Instruct and Step 3.5 Flash
BenchmarkQwen2.5 72B InstructStep 3.5 FlashLeader
τ²-Bench Telecom34.5%94.4%Step 3.5 Flash
METR time horizons35.8%Not measuredOnly Qwen2.5 72B Instruct measured
BALROG16.2%Not measuredOnly Qwen2.5 72B Instruct measured
TheAgentCompany5.7%Not measuredOnly Qwen2.5 72B Instruct measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Qwen2.5 72B Instruct and Step 3.5 Flash
BenchmarkQwen2.5 72B InstructStep 3.5 FlashLeader
GPQA Diamond (Artificial Analysis run)49.1%83.1%Step 3.5 Flash
Humanity's Last Exam (Artificial Analysis run)3.6%24.5%Step 3.5 Flash
GPQA Diamond (Epoch AI run)49.1%Not measuredOnly Qwen2.5 72B Instruct measured
BIG-Bench Hard79.8%Not measuredOnly Qwen2.5 72B Instruct measured
LMArena Text: hard prompts12711411Step 3.5 Flash
LMArena Text: expert12451421Step 3.5 Flash
LMArena Text: hard prompts in English12791421Step 3.5 Flash
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Qwen2.5 72B Instruct and Step 3.5 Flash
BenchmarkQwen2.5 72B InstructStep 3.5 FlashLeader
AA Math Index14.0Not measuredOnly Qwen2.5 72B Instruct measured
AIME 2025 (Artificial Analysis run)14.0%Not measuredOnly Qwen2.5 72B Instruct measured
OTIS Mock AIME8.1%Not measuredOnly Qwen2.5 72B Instruct measured
MATH level 563.2%Not measuredOnly Qwen2.5 72B Instruct measured
LMArena Text: math12831408Step 3.5 Flash
LMArena Text: mathematical work12901421Step 3.5 Flash
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for Qwen2.5 72B Instruct and Step 3.5 Flash
BenchmarkQwen2.5 72B InstructStep 3.5 FlashLeader
MMLU Pro (Artificial Analysis run)72.0%Not measuredOnly Qwen2.5 72B Instruct measured
MMLU85.3%Not measuredOnly Qwen2.5 72B Instruct measured
AI2 Reasoning Challenge94.5%Not measuredOnly Qwen2.5 72B Instruct measured
LMArena Text: science12751415Step 3.5 Flash
LMArena Text: medicine and healthcare12581408Step 3.5 Flash
LMArena Text: legal and government12881408Step 3.5 Flash
LMArena Text: business and finance12531394Step 3.5 Flash
Neither model has a result on the other 11 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Qwen2.5 72B Instruct and Step 3.5 Flash
BenchmarkQwen2.5 72B InstructStep 3.5 FlashLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index017
General benchmarks for Qwen2.5 72B Instruct and Step 3.5 Flash
BenchmarkQwen2.5 72B InstructStep 3.5 FlashLeader
IFBench36.9%66.5%Step 3.5 Flash
Long context reasoning (AA-LCR)Not measured63.0%Only Step 3.5 Flash measured
DTBench62.9%Not measuredOnly Qwen2.5 72B Instruct measured
LMCA13.4%Not measuredOnly Qwen2.5 72B Instruct measured
HellaSwag84.8%Not measuredOnly Qwen2.5 72B Instruct measured
WinoGrande82.3%Not measuredOnly Qwen2.5 72B Instruct measured
PIQA82.6%Not measuredOnly Qwen2.5 72B Instruct measured
LMArena Text12691403Step 3.5 Flash
LMArena Text: instruction following12541385Step 3.5 Flash
LMArena Text: creative writing12211357Step 3.5 Flash
LMArena Text: English12831417Step 3.5 Flash
LMArena Text: non-English12521385Step 3.5 Flash
LMArena Text: Chinese12731446Step 3.5 Flash
LMArena Text: German12341405Step 3.5 Flash
LMArena Text: Japanese11801353Step 3.5 Flash
LMArena Text: Korean11881351Step 3.5 Flash
LMArena Text: French12801421Step 3.5 Flash
LMArena Text: Spanish12551419Step 3.5 Flash
LMArena Text: Russian12641385Step 3.5 Flash
LMArena Text: PolishNot measured1389Only Step 3.5 Flash measured
LMArena Text: multi-turn12721404Step 3.5 Flash
LMArena Text: longer queries12811402Step 3.5 Flash
LMArena Text: writing and language12471372Step 3.5 Flash
LMArena Text: entertainment and media12111360Step 3.5 Flash
Neither model has a result on the other 22 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Qwen2.5 72B Instruct and Step 3.5 Flash
BenchmarkQwen2.5 72B InstructStep 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

Qwen2.5 72B Instruct$0.0006Fits 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

Qwen2.5 72B Instruct$0.019Exceeds the context window
Step 3.5 Flash$0.0059Fits in one request

Step 3.5 Flash costs less

Agent loop

200K input + 10K output tokens

Qwen2.5 72B Instruct$0.076Exceeds the context window
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 Qwen2.5 72B Instruct and Step 3.5 Flash
SpecificationQwen2.5 72B InstructStepFun Step 3.5 Flash
MakerQwenStepFun
WeightsOpen weightsOpen weights
ReleasedSeptember 19, 2024January 29, 2026
Context window33K262K
Input $/Mtok$0.36$0.10
Output $/Mtok$0.40$0.30
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Qwen2.5 72B Instruct better than Step 3.5 Flash for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen2.5 72B Instruct for work measured by Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.

Which is cheaper, Qwen2.5 72B Instruct or Step 3.5 Flash?

Qwen2.5 72B Instruct costs $0.36 per million input tokens and $0.40 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, Qwen2.5 72B Instruct or Step 3.5 Flash?

Step 3.5 Flash, with 262K tokens against 33K.

How many benchmarks is the Qwen2.5 72B Instruct vs Step 3.5 Flash comparison based on?

33 benchmarks have a result for both models as of October 21, 2026. Qwen2.5 72B Instruct's coding index rests on 0 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