Enter opens the highlighted result. Esc closes.

Qwen2.5 72B Instruct vs Qwen3 30B A3B Instruct 2507

Qwen2.5 72B Instruct leads Qwen3 30B A3B Instruct 2507 on the Artificial Analysis Intelligence Index, 7.7 to 7.5, and Qwen3 30B A3B Instruct 2507 costs 1.3x less per output token ($0.30 vs $0.40 per million). Updated October 22, 2026; 41 benchmarks have a result for both.

Replace Qwen2.5 72B Instruct Replace Qwen3 30B A3B Instruct 2507
Qwen2.5 72B InstructQwen
Coding
No data
Overall
26.5
Output $/M
$0.40
2
Qwen3 30B A3B Instruct 2507Qwen
Coding
No data
Overall
41.5
Output $/M
$0.30
39
vs boards won of 41 shared

Qwen2.5 72B Instruct or Qwen3 30B A3B Instruct 2507: 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 LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model AQwen2.5 72B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3 30B A3B Instruct 2507QwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
41
Qwen2.5 72B Instruct only
12
Qwen3 30B A3B Instruct 2507 only
4
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 30B A3B Instruct 2507 not benchmarked.
Widest category
Math, 39.5 points apart on average over 5 shared benchmarks.
Widest single gap
OTIS Mock AIME: Qwen2.5 72B Instruct 8.1% against Qwen3 30B A3B Instruct 2507 62.2%, 54.2 points apart on a 0 to 100 scale.
Output price
Qwen2.5 72B Instruct $0.40 against Qwen3 30B A3B Instruct 2507 $0.30 per million output tokens, 1.3x apart.
Context window
Qwen2.5 72B Instruct takes 33K tokens, Qwen3 30B A3B Instruct 2507 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 30B A3B Instruct 2507Ties
Coding04
Intelligence10
Agentic work10
Reasoning06
Math05
Knowledge05
General019
All shared boards239
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Qwen2.5 72B Instruct and Qwen3 30B A3B Instruct 2507
BenchmarkQwen2.5 72B InstructQwen3 30B A3B Instruct 2507Leader
LiveCodeBench (Artificial Analysis run)27.6%70.7%Qwen3 30B A3B Instruct 2507
SciCodeNot measured33.0%Only Qwen3 30B A3B Instruct 2507 measured
Terminal-Bench Hard (Artificial Analysis run)4.5%6.1%Qwen3 30B A3B Instruct 2507
WeirdML16.0%Not measuredOnly Qwen2.5 72B Instruct measured
LMArena Text: coding12921416Qwen3 30B A3B Instruct 2507
LMArena Text: software and IT12921417Qwen3 30B A3B Instruct 2507
Neither model has a result on the other 37 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Qwen2.5 72B Instruct and Qwen3 30B A3B Instruct 2507
BenchmarkQwen2.5 72B InstructQwen3 30B A3B Instruct 2507Leader
AA Intelligence Index7.77.5Qwen2.5 72B Instruct
Epoch Capabilities Index129.0Not measuredOnly Qwen2.5 72B Instruct measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Qwen2.5 72B Instruct and Qwen3 30B A3B Instruct 2507
BenchmarkQwen2.5 72B InstructQwen3 30B A3B Instruct 2507Leader
τ²-Bench Telecom34.5%28.1%Qwen2.5 72B Instruct
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
Berkeley Function Calling Leaderboard (BFCL)Not measured41.4%Only Qwen3 30B A3B Instruct 2507 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 30B A3B Instruct 2507
BenchmarkQwen2.5 72B InstructQwen3 30B A3B Instruct 2507Leader
GPQA Diamond (Artificial Analysis run)49.1%70.7%Qwen3 30B A3B Instruct 2507
Humanity's Last Exam (Artificial Analysis run)3.6%10.3%Qwen3 30B A3B Instruct 2507
GPQA Diamond (Epoch AI run)49.1%55.6%Qwen3 30B A3B Instruct 2507
BIG-Bench Hard79.8%Not measuredOnly Qwen2.5 72B Instruct measured
LMArena Text: hard prompts12711398Qwen3 30B A3B Instruct 2507
LMArena Text: expert12451397Qwen3 30B A3B Instruct 2507
LMArena Text: hard prompts in English12791406Qwen3 30B A3B Instruct 2507
Neither model has a result on the other 16 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index05
Math benchmarks for Qwen2.5 72B Instruct and Qwen3 30B A3B Instruct 2507
BenchmarkQwen2.5 72B InstructQwen3 30B A3B Instruct 2507Leader
AA Math Index14.066.3Qwen3 30B A3B Instruct 2507
AIME 2025 (Artificial Analysis run)14.0%66.3%Qwen3 30B A3B Instruct 2507
OTIS Mock AIME8.1%62.2%Qwen3 30B A3B Instruct 2507
MATH level 563.2%Not measuredOnly Qwen2.5 72B Instruct measured
LMArena Text: math12831394Qwen3 30B A3B Instruct 2507
LMArena Text: mathematical work12901411Qwen3 30B A3B Instruct 2507
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for Qwen2.5 72B Instruct and Qwen3 30B A3B Instruct 2507
BenchmarkQwen2.5 72B InstructQwen3 30B A3B Instruct 2507Leader
MMLU Pro (Artificial Analysis run)72.0%80.5%Qwen3 30B A3B Instruct 2507
MMLU85.3%Not measuredOnly Qwen2.5 72B Instruct measured
AI2 Reasoning Challenge94.5%Not measuredOnly Qwen2.5 72B Instruct measured
LMArena Text: science12751393Qwen3 30B A3B Instruct 2507
LMArena Text: medicine and healthcare12581392Qwen3 30B A3B Instruct 2507
LMArena Text: legal and government12881387Qwen3 30B A3B Instruct 2507
LMArena Text: business and finance12531389Qwen3 30B A3B Instruct 2507
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 30B A3B Instruct 2507
BenchmarkQwen2.5 72B InstructQwen3 30B A3B Instruct 2507Leader
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 30B A3B Instruct 2507
BenchmarkQwen2.5 72B InstructQwen3 30B A3B Instruct 2507Leader
IFBench36.9%50.7%Qwen3 30B A3B Instruct 2507
Long context reasoning (AA-LCR)Not measured61.3%Only Qwen3 30B A3B Instruct 2507 measured
DTBench62.9%67.2%Qwen3 30B A3B Instruct 2507
LMCA13.4%22.4%Qwen3 30B A3B Instruct 2507
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 Text12691384Qwen3 30B A3B Instruct 2507
LMArena Text: instruction following12541363Qwen3 30B A3B Instruct 2507
LMArena Text: creative writing12211317Qwen3 30B A3B Instruct 2507
LMArena Text: English12831391Qwen3 30B A3B Instruct 2507
LMArena Text: non-English12521372Qwen3 30B A3B Instruct 2507
LMArena Text: Chinese12731432Qwen3 30B A3B Instruct 2507
LMArena Text: German12341379Qwen3 30B A3B Instruct 2507
LMArena Text: Japanese11801337Qwen3 30B A3B Instruct 2507
LMArena Text: Korean11881330Qwen3 30B A3B Instruct 2507
LMArena Text: French12801419Qwen3 30B A3B Instruct 2507
LMArena Text: Spanish12551404Qwen3 30B A3B Instruct 2507
LMArena Text: Russian12641369Qwen3 30B A3B Instruct 2507
LMArena Text: PolishNot measured1353Only Qwen3 30B A3B Instruct 2507 measured
LMArena Text: multi-turn12721378Qwen3 30B A3B Instruct 2507
LMArena Text: longer queries12811378Qwen3 30B A3B Instruct 2507
LMArena Text: writing and language12471336Qwen3 30B A3B Instruct 2507
LMArena Text: entertainment and media12111334Qwen3 30B A3B Instruct 2507
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 30B A3B Instruct 2507
BenchmarkQwen2.5 72B InstructQwen3 30B A3B Instruct 2507Leader
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 30B A3B Instruct 2507$0.0002Fits in one request

Qwen3 30B A3B Instruct 2507 costs less

Repository review

50K input + 3K output tokens

Qwen2.5 72B Instruct$0.019Exceeds the context window
Qwen3 30B A3B Instruct 2507$0.0054Fits in one request

Qwen3 30B A3B Instruct 2507 costs less

Agent loop

200K input + 10K output tokens

Qwen2.5 72B Instruct$0.076Exceeds the context window
Qwen3 30B A3B Instruct 2507$0.021Fits in one request

Qwen3 30B A3B Instruct 2507 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 30B A3B Instruct 2507
SpecificationQwen2.5 72B InstructQwen3 30B A3B Instruct 2507
MakerQwenQwen
WeightsOpen weightsOpen weights
ReleasedSeptember 19, 2024July 29, 2025
Context window33K262K
Input $/Mtok$0.36$0.09
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 Qwen3 30B A3B Instruct 2507 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 LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Which is cheaper, Qwen2.5 72B Instruct or Qwen3 30B A3B Instruct 2507?

Qwen2.5 72B Instruct costs $0.36 per million input tokens and $0.40 per million output tokens; Qwen3 30B A3B Instruct 2507 costs $0.09 and $0.30. Cost per solved task is known for neither of them.

Which has the bigger context window, Qwen2.5 72B Instruct or Qwen3 30B A3B Instruct 2507?

Qwen3 30B A3B Instruct 2507, with 262K tokens against 33K.

How many benchmarks is the Qwen2.5 72B Instruct vs Qwen3 30B A3B Instruct 2507 comparison based on?

41 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 30B A3B Instruct 2507's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next