Enter opens the highlighted result. Esc closes.

Qwen2.5 72B Instruct vs Qwen3.5-27B

Qwen3.5-27B leads Qwen2.5 72B Instruct on the Artificial Analysis Intelligence Index, 22.9 to 7.7, and Qwen2.5 72B Instruct costs 3.9x less per output token ($0.40 vs $1.56 per million). Updated October 22, 2026; 36 benchmarks have a result for both.

Replace Qwen2.5 72B Instruct Replace Qwen3.5-27B
Qwen2.5 72B InstructQwen
Coding
No data
Overall
26.5
Output $/M
$0.40
0
Qwen3.5-27BQwen
Coding
No data
Overall
No data
Output $/M
$1.56
36
vs boards won of 36 shared

Qwen2.5 72B Instruct or Qwen3.5-27B: 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 3.9x cheaper ($0.40 vs $1.56 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or WeirdML, where it leads.

Model AQwen2.5 72B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3.5-27BQwenNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
36
Qwen2.5 72B Instruct only
17
Qwen3.5-27B only
17
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, Qwen3.5-27B not benchmarked.
Widest category
Agentic work, 59.4 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Qwen2.5 72B Instruct 34.5% against Qwen3.5-27B 93.9%, 59.4 points apart on a 0 to 100 scale.
Output price
Qwen2.5 72B Instruct $0.40 against Qwen3.5-27B $1.56 per million output tokens, 3.9x apart.
Context window
Qwen2.5 72B Instruct takes 33K tokens, Qwen3.5-27B 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 InstructBarsQwen3.5-27BTies
Coding04
Intelligence01
Agentic work01
Reasoning05
Math02
Knowledge04
General019
All shared boards036
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Qwen2.5 72B Instruct and Qwen3.5-27B
BenchmarkQwen2.5 72B InstructQwen3.5-27BLeader
LMArena WebDevNot measured1358Only Qwen3.5-27B measured
LiveCodeBench (Artificial Analysis run)27.6%Not measuredOnly Qwen2.5 72B Instruct measured
Terminal-Bench Hard (Artificial Analysis run)4.5%32.6%Qwen3.5-27B
WeirdML16.0%39.5%Qwen3.5-27B
ALE-BenchNot measured349.4Only Qwen3.5-27B measured
LMArena Text: coding12921427Qwen3.5-27B
LMArena Text: software and IT12921431Qwen3.5-27B
LMArena WebDev: ReactNot measured1346Only Qwen3.5-27B measured
LMArena WebDev: HTMLNot measured1386Only Qwen3.5-27B measured
Neither model has a result on the other 30 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Qwen2.5 72B Instruct and Qwen3.5-27B
BenchmarkQwen2.5 72B InstructQwen3.5-27BLeader
AA Intelligence Index7.722.9Qwen3.5-27B
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 Qwen3.5-27B
BenchmarkQwen2.5 72B InstructQwen3.5-27BLeader
τ²-Bench Telecom34.5%93.9%Qwen3.5-27B
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$202Only Qwen3.5-27B measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Qwen2.5 72B Instruct and Qwen3.5-27B
BenchmarkQwen2.5 72B InstructQwen3.5-27BLeader
GPQA Diamond (Artificial Analysis run)49.1%85.8%Qwen3.5-27B
Humanity's Last Exam (Artificial Analysis run)3.6%23.9%Qwen3.5-27B
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 prompts12711415Qwen3.5-27B
LMArena Text: expert12451427Qwen3.5-27B
LMArena Text: hard prompts in English12791429Qwen3.5-27B
LMArena Vision: diagramsNot measured1249Only Qwen3.5-27B measured
LMArena Vision: homeworkNot measured1256Only Qwen3.5-27B measured
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Qwen2.5 72B Instruct and Qwen3.5-27B
BenchmarkQwen2.5 72B InstructQwen3.5-27BLeader
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: math12831429Qwen3.5-27B
LMArena Text: mathematical work12901429Qwen3.5-27B
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 Qwen3.5-27B
BenchmarkQwen2.5 72B InstructQwen3.5-27BLeader
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: science12751437Qwen3.5-27B
LMArena Text: medicine and healthcare12581425Qwen3.5-27B
LMArena Text: legal and government12881405Qwen3.5-27B
LMArena Text: business and finance12531399Qwen3.5-27B
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 Qwen3.5-27B
BenchmarkQwen2.5 72B InstructQwen3.5-27BLeader
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 Qwen3.5-27B
BenchmarkQwen2.5 72B InstructQwen3.5-27BLeader
IFBench36.9%75.6%Qwen3.5-27B
Long context reasoning (AA-LCR)Not measured77.7%Only Qwen3.5-27B measured
DTBench62.9%82.4%Qwen3.5-27B
LMCA13.4%34.0%Qwen3.5-27B
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 Text12691409Qwen3.5-27B
LMArena Text: instruction following12541393Qwen3.5-27B
LMArena Text: creative writing12211362Qwen3.5-27B
LMArena VisionNot measured1241Only Qwen3.5-27B measured
LMArena Text: English12831425Qwen3.5-27B
LMArena Text: non-English12521390Qwen3.5-27B
LMArena Text: Chinese12731478Qwen3.5-27B
LMArena Text: German12341392Qwen3.5-27B
LMArena Text: Japanese11801346Qwen3.5-27B
LMArena Text: Korean11881359Qwen3.5-27B
LMArena Text: French12801410Qwen3.5-27B
LMArena Text: Spanish12551407Qwen3.5-27B
LMArena Text: Russian12641390Qwen3.5-27B
LMArena Text: PolishNot measured1375Only Qwen3.5-27B measured
LMArena Text: multi-turn12721410Qwen3.5-27B
LMArena Text: longer queries12811413Qwen3.5-27B
LMArena Text: writing and language12471380Qwen3.5-27B
LMArena Text: entertainment and media12111363Qwen3.5-27B
LMArena Vision: EnglishNot measured1246Only Qwen3.5-27B measured
LMArena Vision: ChineseNot measured1301Only Qwen3.5-27B measured
LMArena Vision: reading textNot measured1246Only Qwen3.5-27B measured
LMArena Vision: humorNot measured1227Only Qwen3.5-27B measured
LMArena Vision: captioningNot measured1170Only Qwen3.5-27B measured
LMArena Vision: recognizing thingsNot measured1210Only Qwen3.5-27B measured
LMArena Vision: creative writingNot measured1224Only Qwen3.5-27B measured
Neither model has a result on the other 14 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 Qwen3.5-27B
BenchmarkQwen2.5 72B InstructQwen3.5-27BLeader
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
Qwen3.5-27B$0.0010Fits 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
Qwen3.5-27B$0.014Fits in one request

Qwen3.5-27B costs less

Agent loop

200K input + 10K output tokens

Qwen2.5 72B Instruct$0.076Exceeds the context window
Qwen3.5-27B$0.055Fits in one request

Qwen3.5-27B 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 Qwen3.5-27B
SpecificationQwen2.5 72B InstructQwen3.5-27B
MakerQwenQwen
WeightsOpen weightsOpen weights
ReleasedSeptember 19, 2024February 25, 2026
Context window33K262K
Input $/Mtok$0.36$0.195
Output $/Mtok$0.40$1.56
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 Qwen3.5-27B 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 3.9x cheaper ($0.40 vs $1.56 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or WeirdML, where it leads.

Which is cheaper, Qwen2.5 72B Instruct or Qwen3.5-27B?

Qwen2.5 72B Instruct costs $0.36 per million input tokens and $0.40 per million output tokens; Qwen3.5-27B costs $0.195 and $1.56. Cost per solved task is known for neither of them.

Which has the bigger context window, Qwen2.5 72B Instruct or Qwen3.5-27B?

Qwen3.5-27B, with 262K tokens against 33K.

How many benchmarks is the Qwen2.5 72B Instruct vs Qwen3.5-27B comparison based on?

36 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 Qwen3.5-27B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next