Enter opens the highlighted result. Esc closes.

Nova Pro 1.0 vs Qwen3 235B A22B Thinking 2507

Qwen3 235B A22B Thinking 2507 leads Nova Pro 1.0 on the Artificial Analysis Intelligence Index, 12.7 to 7.0, at about the same output price ($3.50 vs $3.20 per million). Updated October 22, 2026; 28 benchmarks have a result for both.

Replace Nova Pro 1.0 Replace Qwen3 235B A22B Thinking 2507
Nova Pro 1.0Amazon
Coding
No data
Overall
No data
Output $/M
$3.20
0
Qwen3 235B A22B Thinking 2507Qwen
Coding
No data
Overall
52.9
Output $/M
$3.50
28
vs boards won of 28 shared

Nova Pro 1.0 or Qwen3 235B A22B Thinking 2507: which to pick

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

Pick Nova Pro 1.0 for output tokens 1.1x cheaper ($3.20 vs $3.50 per million) and a larger context window (300K against 128K tokens).

Model ANova Pro 1.0AmazonNot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3 235B A22B Thinking 2507QwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
28
Nova Pro 1.0 only
14
Qwen3 235B A22B Thinking 2507 only
18
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, Qwen3 235B A22B Thinking 2507 not benchmarked.
Widest category
Reasoning, 33.1 points apart on average over 3 shared benchmarks.
Widest single gap
LMArena Text: expert: Nova Pro 1.0 1211 against Qwen3 235B A22B Thinking 2507 1463, 42.1 points apart on a 0 to 100 scale.
Output price
Nova Pro 1.0 $3.20 against Qwen3 235B A22B Thinking 2507 $3.50 per million output tokens, 1.1x apart.
Context window
Nova Pro 1.0 takes 300K tokens, Qwen3 235B A22B Thinking 2507 128K.

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 1.0BarsQwen3 235B A22B Thinking 2507Ties
Coding02
Intelligence01
Reasoning03
Math02
Knowledge04
Web design01
General015
All shared boards028
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
Coding benchmarks for Nova Pro 1.0 and Qwen3 235B A22B Thinking 2507
BenchmarkNova Pro 1.0Qwen3 235B A22B Thinking 2507Leader
AA Coding IndexNot measured22.1Only Qwen3 235B A22B Thinking 2507 measured
LiveCodeBench (Artificial Analysis run)23.3%Not measuredOnly Nova Pro 1.0 measured
Terminal-Bench Hard (Artificial Analysis run)6.1%Not measuredOnly Nova Pro 1.0 measured
WeirdMLNot measured41.0%Only Qwen3 235B A22B Thinking 2507 measured
LMArena Text: coding12701424Qwen3 235B A22B Thinking 2507
LMArena Text: software and IT12711431Qwen3 235B A22B Thinking 2507
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 Qwen3 235B A22B Thinking 2507
BenchmarkNova Pro 1.0Qwen3 235B A22B Thinking 2507Leader
AA Intelligence Index7.012.7Qwen3 235B A22B Thinking 2507
Neither model has a result on the other 1 board here
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Agentic work benchmarks for Nova Pro 1.0 and Qwen3 235B A22B Thinking 2507
BenchmarkNova Pro 1.0Qwen3 235B A22B Thinking 2507Leader
AA Agentic IndexNot measured1.3Only Qwen3 235B A22B Thinking 2507 measured
τ²-Bench Telecom14.0%Not measuredOnly Nova Pro 1.0 measured
Vending-Bench 2Not measured-$11Only Qwen3 235B A22B Thinking 2507 measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
Reasoning benchmarks for Nova Pro 1.0 and Qwen3 235B A22B Thinking 2507
BenchmarkNova Pro 1.0Qwen3 235B A22B Thinking 2507Leader
GPQA Diamond (Artificial Analysis run)49.9%Not measuredOnly Nova Pro 1.0 measured
Humanity's Last Exam (Artificial Analysis run)3.2%Not measuredOnly Nova Pro 1.0 measured
GPQA Diamond (Epoch AI run)Not measured80.1%Only Qwen3 235B A22B Thinking 2507 measured
Mystery game puzzlesNot measured9.0%Only Qwen3 235B A22B Thinking 2507 measured
LMArena Text: hard prompts12461416Qwen3 235B A22B Thinking 2507
LMArena Text: expert12111463Qwen3 235B A22B Thinking 2507
LMArena Text: hard prompts in English12591432Qwen3 235B A22B Thinking 2507
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 Nova Pro 1.0 and Qwen3 235B A22B Thinking 2507
BenchmarkNova Pro 1.0Qwen3 235B A22B Thinking 2507Leader
AA Math Index7.0Not measuredOnly Nova Pro 1.0 measured
AIME 2025 (Artificial Analysis run)7.0%Not measuredOnly Nova Pro 1.0 measured
OTIS Mock AIMENot measured86.7%Only Qwen3 235B A22B Thinking 2507 measured
LMArena Text: math12521412Qwen3 235B A22B Thinking 2507
LMArena Text: mathematical work12611435Qwen3 235B A22B Thinking 2507
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for Nova Pro 1.0 and Qwen3 235B A22B Thinking 2507
BenchmarkNova Pro 1.0Qwen3 235B A22B Thinking 2507Leader
MMLU Pro (Artificial Analysis run)69.1%Not measuredOnly Nova Pro 1.0 measured
SimpleQA VerifiedNot measured40.4%Only Qwen3 235B A22B Thinking 2507 measured
MMLU82.0%Not measuredOnly Nova Pro 1.0 measured
LMArena Text: science12551433Qwen3 235B A22B Thinking 2507
LMArena Text: medicine and healthcare12601456Qwen3 235B A22B Thinking 2507
LMArena Text: legal and government12811415Qwen3 235B A22B Thinking 2507
LMArena Text: business and finance12291413Qwen3 235B A22B Thinking 2507
Neither model has a result on the other 11 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index01
Web design benchmarks for Nova Pro 1.0 and Qwen3 235B A22B Thinking 2507
BenchmarkNova Pro 1.0Qwen3 235B A22B Thinking 2507Leader
Design Arena: websites7961052Qwen3 235B A22B Thinking 2507
Design Arena: UI componentsNot measured942Only Qwen3 235B A22B Thinking 2507 measured
Design Arena: game devNot measured956Only Qwen3 235B A22B Thinking 2507 measured
Design Arena: data vizNot measured950Only Qwen3 235B A22B Thinking 2507 measured
Design Arena: 3DNot measured997Only Qwen3 235B A22B Thinking 2507 measured
Design Arena: all code categoriesNot measured1032Only Qwen3 235B A22B Thinking 2507 measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index015
General benchmarks for Nova Pro 1.0 and Qwen3 235B A22B Thinking 2507
BenchmarkNova Pro 1.0Qwen3 235B A22B Thinking 2507Leader
IFBench38.1%Not measuredOnly Nova Pro 1.0 measured
Long context reasoning (AA-LCR)21.0%Not measuredOnly Nova Pro 1.0 measured
DTBenchNot measured80.3%Only Qwen3 235B A22B Thinking 2507 measured
LMCANot measured29.3%Only Qwen3 235B A22B Thinking 2507 measured
Fiction.LiveBenchNot measured75.0%Only Qwen3 235B A22B Thinking 2507 measured
Creative writing (Lech Mazur)Not measured82.4%Only Qwen3 235B A22B Thinking 2507 measured
LMArena Text12591415Qwen3 235B A22B Thinking 2507
LMArena Text: instruction following12351386Qwen3 235B A22B Thinking 2507
LMArena Text: creative writing12121384Qwen3 235B A22B Thinking 2507
LMArena Vision980Not measuredOnly Nova Pro 1.0 measured
LMArena Text: English12761429Qwen3 235B A22B Thinking 2507
LMArena Text: non-English12331397Qwen3 235B A22B Thinking 2507
LMArena Text: Chinese12441481Qwen3 235B A22B Thinking 2507
LMArena Text: German12431408Qwen3 235B A22B Thinking 2507
LMArena Text: Japanese12001386Qwen3 235B A22B Thinking 2507
LMArena Text: Korean12031375Qwen3 235B A22B Thinking 2507
LMArena Text: French1271Not measuredOnly Nova Pro 1.0 measured
LMArena Text: Spanish11821389Qwen3 235B A22B Thinking 2507
LMArena Text: Russian12401401Qwen3 235B A22B Thinking 2507
LMArena Text: PolishNot measured1390Only Qwen3 235B A22B Thinking 2507 measured
LMArena Text: multi-turn12461406Qwen3 235B A22B Thinking 2507
LMArena Text: longer queries12551400Qwen3 235B A22B Thinking 2507
LMArena Text: writing and language12471388Qwen3 235B A22B Thinking 2507
LMArena Text: entertainment and media12101370Qwen3 235B A22B Thinking 2507
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 Qwen3 235B A22B Thinking 2507
BenchmarkNova Pro 1.0Qwen3 235B A22B Thinking 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

Nova Pro 1.0$0.0024Fits in one request
Qwen3 235B A22B Thinking 2507$0.0022Fits in one request

Qwen3 235B A22B Thinking 2507 costs less

Repository review

50K input + 3K output tokens

Nova Pro 1.0$0.050Fits in one request
Qwen3 235B A22B Thinking 2507$0.033Fits in one request

Qwen3 235B A22B Thinking 2507 costs less

Agent loop

200K input + 10K output tokens

Nova Pro 1.0$0.192Fits in one request
Qwen3 235B A22B Thinking 2507$0.125Exceeds the context window

Qwen3 235B A22B Thinking 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 Nova Pro 1.0 and Qwen3 235B A22B Thinking 2507
SpecificationAmazon Nova Pro 1.0Qwen3 235B A22B Thinking 2507
MakerAmazonQwen
WeightsNo public weights listedOpen weights
ReleasedDecember 5, 2024July 25, 2025
Context window300K128K
Input $/Mtok$0.80$0.45
Output $/Mtok$3.20$3.50
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 Qwen3 235B A22B Thinking 2507 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Nova Pro 1.0 for output tokens 1.1x cheaper ($3.20 vs $3.50 per million) and a larger context window (300K against 128K tokens).

Which is cheaper, Nova Pro 1.0 or Qwen3 235B A22B Thinking 2507?

Nova Pro 1.0 costs $0.80 per million input tokens and $3.20 per million output tokens; Qwen3 235B A22B Thinking 2507 costs $0.45 and $3.50. Cost per solved task is known for neither of them.

Which has the bigger context window, Nova Pro 1.0 or Qwen3 235B A22B Thinking 2507?

Nova Pro 1.0, with 300K tokens against 128K.

How many benchmarks is the Nova Pro 1.0 vs Qwen3 235B A22B Thinking 2507 comparison based on?

28 benchmarks have a result for both models as of October 22, 2026. Nova Pro 1.0's coding index rests on 0 independent benchmarks and Qwen3 235B A22B Thinking 2507's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next