Enter opens the highlighted result. Esc closes.

Nova Pro 1.0 vs Qwen2.5 72B Instruct

Qwen2.5 72B Instruct leads Nova Pro 1.0 on the Artificial Analysis Intelligence Index, 7.7 to 7.0, and Qwen2.5 72B Instruct costs 8.0x less per output token ($0.40 vs $3.20 per million). Updated October 21, 2026; 38 benchmarks have a result for both.

Replace Nova Pro 1.0 Replace Qwen2.5 72B Instruct
Nova Pro 1.0Amazon
Coding
No data
Overall
7.0
Output $/M
$3.20
7
Qwen2.5 72B InstructQwen
Coding
No data
Overall
7.7
Output $/M
$0.40
31
vs boards won of 38 shared

Nova Pro 1.0 or Qwen2.5 72B Instruct: which to pick

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

Pick Nova Pro 1.0 for a larger context window (300K against 33K tokens) and work measured by LiveCodeBench (Artificial Analysis run) or LMArena Text: coding, where it leads.

Model ANova Pro 1.0AmazonNot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen2.5 72B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
38
Nova Pro 1.0 only
4
Qwen2.5 72B Instruct only
15
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
Nova Pro 1.0 not benchmarked, Qwen2.5 72B Instruct not benchmarked.
Widest category
Agentic work, 20.5 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Nova Pro 1.0 14.0% against Qwen2.5 72B Instruct 34.5%, 20.5 points apart on a 0 to 100 scale.
Output price
Nova Pro 1.0 $3.20 against Qwen2.5 72B Instruct $0.40 per million output tokens, 8.0x apart.
Context window
Nova Pro 1.0 takes 300K tokens, Qwen2.5 72B Instruct 33K.

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
CategoryNova Pro 1.0BarsQwen2.5 72B InstructTies
Coding13
Intelligence01
Agentic work01
Reasoning14
Math04
Knowledge15
General413
All shared boards731
CodingLike-for-likeSix of these boards feed the Vibe Coding Index13
Coding benchmarks for Nova Pro 1.0 and Qwen2.5 72B Instruct
BenchmarkNova Pro 1.0Qwen2.5 72B InstructLeader
LiveCodeBench (Artificial Analysis run)23.3%27.6%Qwen2.5 72B Instruct
Terminal-Bench Hard (Artificial Analysis run)6.1%4.5%Nova Pro 1.0
WeirdMLNot measured16.0%Only Qwen2.5 72B Instruct measured
LMArena Text: coding12701292Qwen2.5 72B Instruct
LMArena Text: software and IT12711292Qwen2.5 72B Instruct
Neither model has a result on the other 33 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Nova Pro 1.0 and Qwen2.5 72B Instruct
BenchmarkNova Pro 1.0Qwen2.5 72B InstructLeader
AA Intelligence Index7.07.7Qwen2.5 72B Instruct
Epoch Capabilities IndexNot measured129.0Only Qwen2.5 72B Instruct measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Nova Pro 1.0 and Qwen2.5 72B Instruct
BenchmarkNova Pro 1.0Qwen2.5 72B InstructLeader
τ²-Bench Telecom14.0%34.5%Qwen2.5 72B Instruct
METR time horizonsNot measured35.8%Only Qwen2.5 72B Instruct measured
BALROGNot measured16.2%Only Qwen2.5 72B Instruct measured
TheAgentCompanyNot measured5.7%Only Qwen2.5 72B Instruct measured
Neither model has a result on the other 35 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index14
Reasoning benchmarks for Nova Pro 1.0 and Qwen2.5 72B Instruct
BenchmarkNova Pro 1.0Qwen2.5 72B InstructLeader
GPQA Diamond (Artificial Analysis run)49.9%49.1%Nova Pro 1.0
Humanity's Last Exam (Artificial Analysis run)3.2%3.6%Qwen2.5 72B Instruct
GPQA Diamond (Epoch AI run)Not measured49.1%Only Qwen2.5 72B Instruct measured
BIG-Bench HardNot measured79.8%Only Qwen2.5 72B Instruct measured
LMArena Text: hard prompts12461271Qwen2.5 72B Instruct
LMArena Text: expert12111245Qwen2.5 72B Instruct
LMArena Text: hard prompts in English12591279Qwen2.5 72B Instruct
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index04
Math benchmarks for Nova Pro 1.0 and Qwen2.5 72B Instruct
BenchmarkNova Pro 1.0Qwen2.5 72B InstructLeader
AA Math Index7.014.0Qwen2.5 72B Instruct
AIME 2025 (Artificial Analysis run)7.0%14.0%Qwen2.5 72B Instruct
OTIS Mock AIMENot measured8.1%Only Qwen2.5 72B Instruct measured
MATH level 5Not measured63.2%Only Qwen2.5 72B Instruct measured
LMArena Text: math12521283Qwen2.5 72B Instruct
LMArena Text: mathematical work12611290Qwen2.5 72B Instruct
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index15
Knowledge benchmarks for Nova Pro 1.0 and Qwen2.5 72B Instruct
BenchmarkNova Pro 1.0Qwen2.5 72B InstructLeader
MMLU Pro (Artificial Analysis run)69.1%72.0%Qwen2.5 72B Instruct
MMLU82.0%85.3%Qwen2.5 72B Instruct
AI2 Reasoning ChallengeNot measured94.5%Only Qwen2.5 72B Instruct measured
LMArena Text: science12551275Qwen2.5 72B Instruct
LMArena Text: medicine and healthcare12601258Nova Pro 1.0
LMArena Text: legal and government12811288Qwen2.5 72B Instruct
LMArena Text: business and finance12291253Qwen2.5 72B Instruct
Neither model has a result on the other 10 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Web design benchmarks for Nova Pro 1.0 and Qwen2.5 72B Instruct
BenchmarkNova Pro 1.0Qwen2.5 72B InstructLeader
Design Arena: websites796Not measuredOnly Nova Pro 1.0 measured
Neither model has a result on the other 8 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index413
General benchmarks for Nova Pro 1.0 and Qwen2.5 72B Instruct
BenchmarkNova Pro 1.0Qwen2.5 72B InstructLeader
IFBench38.1%36.9%Nova Pro 1.0
Long context reasoning (AA-LCR)21.0%Not measuredOnly Nova Pro 1.0 measured
DTBenchNot measured62.9%Only Qwen2.5 72B Instruct measured
LMCANot measured13.4%Only Qwen2.5 72B Instruct measured
HellaSwagNot measured84.8%Only Qwen2.5 72B Instruct measured
WinoGrandeNot measured82.3%Only Qwen2.5 72B Instruct measured
PIQANot measured82.6%Only Qwen2.5 72B Instruct measured
LMArena Text12591269Qwen2.5 72B Instruct
LMArena Text: instruction following12351254Qwen2.5 72B Instruct
LMArena Text: creative writing12121221Qwen2.5 72B Instruct
LMArena Vision980Not measuredOnly Nova Pro 1.0 measured
LMArena Text: English12761283Qwen2.5 72B Instruct
LMArena Text: non-English12331252Qwen2.5 72B Instruct
LMArena Text: Chinese12441273Qwen2.5 72B Instruct
LMArena Text: German12431234Nova Pro 1.0
LMArena Text: Japanese12001180Nova Pro 1.0
LMArena Text: Korean12031188Nova Pro 1.0
LMArena Text: French12711280Qwen2.5 72B Instruct
LMArena Text: Spanish11821255Qwen2.5 72B Instruct
LMArena Text: Russian12401264Qwen2.5 72B Instruct
LMArena Text: multi-turn12461272Qwen2.5 72B Instruct
LMArena Text: longer queries12551281Qwen2.5 72B Instruct
LMArena Text: writing and language12471247Qwen2.5 72B Instruct
LMArena Text: entertainment and media12101211Qwen2.5 72B Instruct
LMArena Vision: English987Not measuredOnly Nova Pro 1.0 measured
Neither model has a result on the other 21 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Nova Pro 1.0 and Qwen2.5 72B Instruct
BenchmarkNova Pro 1.0Qwen2.5 72B InstructLeader
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

Nova Pro 1.0$0.0024Fits in one request
Qwen2.5 72B Instruct$0.0006Fits in one request

Qwen2.5 72B Instruct costs less

Repository review

50K input + 3K output tokens

Nova Pro 1.0$0.050Fits in one request
Qwen2.5 72B Instruct$0.019Exceeds the context window

Qwen2.5 72B Instruct costs less

Agent loop

200K input + 10K output tokens

Nova Pro 1.0$0.192Fits in one request
Qwen2.5 72B Instruct$0.076Exceeds the context window

Qwen2.5 72B Instruct 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 Nova Pro 1.0 and Qwen2.5 72B Instruct
SpecificationAmazon Nova Pro 1.0Qwen2.5 72B Instruct
MakerAmazonQwen
WeightsNo public weights listedOpen weights
ReleasedDecember 5, 2024September 19, 2024
Context window300K33K
Input $/Mtok$0.80$0.36
Output $/Mtok$3.20$0.40
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Nova Pro 1.0 better than Qwen2.5 72B Instruct for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Nova Pro 1.0 for a larger context window (300K against 33K tokens) and work measured by LiveCodeBench (Artificial Analysis run) or LMArena Text: coding, where it leads.

Which is cheaper, Nova Pro 1.0 or Qwen2.5 72B Instruct?

Nova Pro 1.0 costs $0.80 per million input tokens and $3.20 per million output tokens; Qwen2.5 72B Instruct costs $0.36 and $0.40. Cost per solved task is known for neither of them.

Which has the bigger context window, Nova Pro 1.0 or Qwen2.5 72B Instruct?

Nova Pro 1.0, with 300K tokens against 33K.

How many benchmarks is the Nova Pro 1.0 vs Qwen2.5 72B Instruct comparison based on?

38 benchmarks have a result for both models as of October 21, 2026. Nova Pro 1.0's coding index rests on 0 independent benchmarks and Qwen2.5 72B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next