Enter opens the highlighted result. Esc closes.

Qwen2.5 72B Instruct vs Qwen3.5-35B-A3B

Qwen3.5-35B-A3B leads Qwen2.5 72B Instruct on the Artificial Analysis Intelligence Index, 19.3 to 7.7, and Qwen2.5 72B Instruct costs 3.3x less per output token ($0.40 vs $1.30 per million). Updated October 22, 2026; 38 benchmarks have a result for both.

Replace Qwen2.5 72B Instruct Replace Qwen3.5-35B-A3B
Qwen2.5 72B InstructQwen
Coding
No data
Overall
26.5
Output $/M
$0.40
0
Qwen3.5-35B-A3BQwen
Coding
No data
Overall
53.5
Output $/M
$1.30
38
vs boards won of 38 shared

Qwen2.5 72B Instruct or Qwen3.5-35B-A3B: which to pick

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

Pick Qwen2.5 72B Instruct for output tokens 3.3x cheaper ($0.40 vs $1.30 per million) and 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 BQwen3.5-35B-A3BQwenNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
38
Qwen2.5 72B Instruct only
15
Qwen3.5-35B-A3B only
8
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, Qwen3.5-35B-A3B not benchmarked.
Widest category
Agentic work, 54.7 points apart on average over 1 shared benchmark.
Widest single gap
OTIS Mock AIME: Qwen2.5 72B Instruct 8.1% against Qwen3.5-35B-A3B 70.0%, 61.9 points apart on a 0 to 100 scale.
Output price
Qwen2.5 72B Instruct $0.40 against Qwen3.5-35B-A3B $1.30 per million output tokens, 3.3x apart.
Context window
Qwen2.5 72B Instruct takes 33K tokens, Qwen3.5-35B-A3B 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 InstructBarsQwen3.5-35B-A3BTies
Coding03
Intelligence02
Agentic work01
Reasoning06
Math03
Knowledge04
General019
All shared boards038
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for Qwen2.5 72B Instruct and Qwen3.5-35B-A3B
BenchmarkQwen2.5 72B InstructQwen3.5-35B-A3BLeader
LMArena WebDevNot measured1254Only Qwen3.5-35B-A3B measured
LiveCodeBench (Artificial Analysis run)27.6%Not measuredOnly Qwen2.5 72B Instruct measured
Terminal-Bench Hard (Artificial Analysis run)4.5%26.5%Qwen3.5-35B-A3B
WeirdML16.0%Not measuredOnly Qwen2.5 72B Instruct measured
ALE-BenchNot measured221.8Only Qwen3.5-35B-A3B measured
LMArena Text: coding12921410Qwen3.5-35B-A3B
LMArena Text: software and IT12921415Qwen3.5-35B-A3B
LMArena WebDev: ReactNot measured1238Only Qwen3.5-35B-A3B measured
LMArena WebDev: HTMLNot measured1301Only Qwen3.5-35B-A3B measured
Neither model has a result on the other 34 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Qwen2.5 72B Instruct and Qwen3.5-35B-A3B
BenchmarkQwen2.5 72B InstructQwen3.5-35B-A3BLeader
AA Intelligence Index7.719.3Qwen3.5-35B-A3B
Epoch Capabilities Index129.0142.5Qwen3.5-35B-A3B
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Qwen2.5 72B Instruct and Qwen3.5-35B-A3B
BenchmarkQwen2.5 72B InstructQwen3.5-35B-A3BLeader
τ²-Bench Telecom34.5%89.2%Qwen3.5-35B-A3B
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
Vending-Bench 2Not measured$463Only Qwen3.5-35B-A3B measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
Reasoning benchmarks for Qwen2.5 72B Instruct and Qwen3.5-35B-A3B
BenchmarkQwen2.5 72B InstructQwen3.5-35B-A3BLeader
GPQA Diamond (Artificial Analysis run)49.1%84.5%Qwen3.5-35B-A3B
Humanity's Last Exam (Artificial Analysis run)3.6%21.0%Qwen3.5-35B-A3B
GPQA Diamond (Epoch AI run)49.1%83.5%Qwen3.5-35B-A3B
BIG-Bench Hard79.8%Not measuredOnly Qwen2.5 72B Instruct measured
LMArena Text: hard prompts12711400Qwen3.5-35B-A3B
LMArena Text: expert12451408Qwen3.5-35B-A3B
LMArena Text: hard prompts in English12791411Qwen3.5-35B-A3B
Neither model has a result on the other 16 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Qwen2.5 72B Instruct and Qwen3.5-35B-A3B
BenchmarkQwen2.5 72B InstructQwen3.5-35B-A3BLeader
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%70.0%Qwen3.5-35B-A3B
MATH level 563.2%Not measuredOnly Qwen2.5 72B Instruct measured
LMArena Text: math12831404Qwen3.5-35B-A3B
LMArena Text: mathematical work12901410Qwen3.5-35B-A3B
MathArenaNot measured14.7%Only Qwen3.5-35B-A3B measured
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 Qwen3.5-35B-A3B
BenchmarkQwen2.5 72B InstructQwen3.5-35B-A3BLeader
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: science12751413Qwen3.5-35B-A3B
LMArena Text: medicine and healthcare12581421Qwen3.5-35B-A3B
LMArena Text: legal and government12881399Qwen3.5-35B-A3B
LMArena Text: business and finance12531394Qwen3.5-35B-A3B
Neither model has a result on the other 13 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 Qwen3.5-35B-A3B
BenchmarkQwen2.5 72B InstructQwen3.5-35B-A3BLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index019
General benchmarks for Qwen2.5 72B Instruct and Qwen3.5-35B-A3B
BenchmarkQwen2.5 72B InstructQwen3.5-35B-A3BLeader
IFBench36.9%72.5%Qwen3.5-35B-A3B
Long context reasoning (AA-LCR)Not measured72.0%Only Qwen3.5-35B-A3B measured
DTBench62.9%80.0%Qwen3.5-35B-A3B
LMCA13.4%29.5%Qwen3.5-35B-A3B
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 Text12691395Qwen3.5-35B-A3B
LMArena Text: instruction following12541379Qwen3.5-35B-A3B
LMArena Text: creative writing12211347Qwen3.5-35B-A3B
LMArena Text: English12831407Qwen3.5-35B-A3B
LMArena Text: non-English12521378Qwen3.5-35B-A3B
LMArena Text: Chinese12731457Qwen3.5-35B-A3B
LMArena Text: German12341367Qwen3.5-35B-A3B
LMArena Text: Japanese11801326Qwen3.5-35B-A3B
LMArena Text: Korean11881355Qwen3.5-35B-A3B
LMArena Text: French12801412Qwen3.5-35B-A3B
LMArena Text: Spanish12551390Qwen3.5-35B-A3B
LMArena Text: Russian12641376Qwen3.5-35B-A3B
LMArena Text: PolishNot measured1385Only Qwen3.5-35B-A3B measured
LMArena Text: multi-turn12721390Qwen3.5-35B-A3B
LMArena Text: longer queries12811389Qwen3.5-35B-A3B
LMArena Text: writing and language12471365Qwen3.5-35B-A3B
LMArena Text: entertainment and media12111347Qwen3.5-35B-A3B
Neither model has a result on the other 24 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 Qwen3.5-35B-A3B
BenchmarkQwen2.5 72B InstructQwen3.5-35B-A3BLeader
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
Qwen3.5-35B-A3B$0.0008Fits in one request

Qwen2.5 72B Instruct costs less

Repository review

50K input + 3K output tokens

Qwen2.5 72B Instruct$0.019Exceeds the context window
Qwen3.5-35B-A3B$0.012Fits in one request

Qwen3.5-35B-A3B costs less

Agent loop

200K input + 10K output tokens

Qwen2.5 72B Instruct$0.076Exceeds the context window
Qwen3.5-35B-A3B$0.045Fits in one request

Qwen3.5-35B-A3B 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 Qwen3.5-35B-A3B
SpecificationQwen2.5 72B InstructQwen3.5-35B-A3B
MakerQwenQwen
WeightsOpen weightsOpen weights
ReleasedSeptember 19, 2024February 25, 2026
Context window33K262K
Input $/Mtok$0.36$0.1625
Output $/Mtok$0.40$1.30
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Qwen2.5 72B Instruct better than Qwen3.5-35B-A3B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen2.5 72B Instruct for output tokens 3.3x cheaper ($0.40 vs $1.30 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.

Which is cheaper, Qwen2.5 72B Instruct or Qwen3.5-35B-A3B?

Qwen2.5 72B Instruct costs $0.36 per million input tokens and $0.40 per million output tokens; Qwen3.5-35B-A3B costs $0.1625 and $1.30. Cost per solved task is known for neither of them.

Which has the bigger context window, Qwen2.5 72B Instruct or Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B, with 262K tokens against 33K.

How many benchmarks is the Qwen2.5 72B Instruct vs Qwen3.5-35B-A3B comparison based on?

38 benchmarks have a result for both models as of October 22, 2026. Qwen2.5 72B Instruct's coding index rests on 0 independent benchmarks and Qwen3.5-35B-A3B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next