Enter opens the highlighted result. Esc closes.

Nova Pro 1.0 vs Claude Opus 4.5

Claude Opus 4.5 leads Nova Pro 1.0 on the Artificial Analysis Intelligence Index, 29.1 to 7.0, and Nova Pro 1.0 costs 7.8x less per output token ($3.20 vs $25.00 per million). Updated October 21, 2026; 39 benchmarks have a result for both.

Replace Nova Pro 1.0 Replace Claude Opus 4.5
Nova Pro 1.0Amazon
Coding
No data
Overall
7.0
Output $/M
$3.20
0
Claude Opus 4.5Anthropic
Coding
44.0
Overall
29.1
Output $/M
$25.00
39
vs boards won of 39 shared

Nova Pro 1.0 or Claude Opus 4.5: which to pick

Only Claude Opus 4.5 has a coding score, 44.0 on the Vibe Coding Index; Nova Pro 1.0 has none, so the two cannot be ranked on coding.

Pick Nova Pro 1.0 for output tokens 7.8x cheaper ($3.20 vs $25.00 per million) and a larger context window (300K against 200K tokens).

Model ANova Pro 1.0AmazonNot benchmarkedNo coding benchmarkNo cost per solved taskModel BClaude Opus 4.5Anthropic44.0/1003 independent benchmarks$1.37 per solved task
Shared results
39
Nova Pro 1.0 only
3
Claude Opus 4.5 only
66
Like-for-like categories
8 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, Claude Opus 4.5 44.0 from 3 benchmarks.
Widest category
Agentic work, 75.4 points apart on average over 1 shared benchmark.
Widest single gap
AIME 2025 (Artificial Analysis run): Nova Pro 1.0 7.0% against Claude Opus 4.5 91.3%, 84.3 points apart on a 0 to 100 scale.
Output price
Nova Pro 1.0 $3.20 against Claude Opus 4.5 $25.00 per million output tokens, 7.8x apart.
Context window
Nova Pro 1.0 takes 300K tokens, Claude Opus 4.5 200K.

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 1.0BarsClaude Opus 4.5Ties
Coding04
Intelligence01
Agentic work01
Reasoning05
Math04
Knowledge05
Web design01
General018
All shared boards039
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Nova Pro 1.0 and Claude Opus 4.5
BenchmarkNova Pro 1.0Claude Opus 4.5Leader
SWE-bench VerifiedNot measured79.2%Only Claude Opus 4.5 measured
SWE-bench (full test set)Not measured52.6%Only Claude Opus 4.5 measured
SWE-bench MultilingualNot measured70.7%Only Claude Opus 4.5 measured
LMArena WebDevNot measured1494Only Claude Opus 4.5 measured
LiveCodeBench (Vals AI)Not measured83.7%Only Claude Opus 4.5 measured
SWE-bench Verified (Vals AI)Not measured76.4%Only Claude Opus 4.5 measured
Vibe Code Bench (Vals AI)Not measured20.6%Only Claude Opus 4.5 measured
LiveCodeBench (Artificial Analysis run)23.3%87.1%Claude Opus 4.5
Terminal-Bench Hard (Artificial Analysis run)6.1%47.0%Claude Opus 4.5
Terminal-BenchNot measured63.1%Only Claude Opus 4.5 measured
GSO-BenchNot measured26.5%Only Claude Opus 4.5 measured
WeirdMLNot measured63.7%Only Claude Opus 4.5 measured
CybenchNot measured82.0%Only Claude Opus 4.5 measured
LMArena Text: coding12701503Claude Opus 4.5
LMArena Text: software and IT12711483Claude Opus 4.5
LMArena WebDev: ReactNot measured1478Only Claude Opus 4.5 measured
LMArena WebDev: HTMLNot measured1510Only Claude Opus 4.5 measured
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Nova Pro 1.0 and Claude Opus 4.5
BenchmarkNova Pro 1.0Claude Opus 4.5Leader
AA Intelligence Index7.029.1Claude Opus 4.5
Epoch Capabilities IndexNot measured150.1Only Claude Opus 4.5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Nova Pro 1.0 and Claude Opus 4.5
BenchmarkNova Pro 1.0Claude Opus 4.5Leader
Design Arena: agents building web appsNot measured1159Only Claude Opus 4.5 measured
Design Arena: agents building full-stack appsNot measured1156Only Claude Opus 4.5 measured
Design Arena: agents building mobile appsNot measured1189Only Claude Opus 4.5 measured
Design Arena: agents building Android appsNot measured1175Only Claude Opus 4.5 measured
τ²-Bench Telecom14.0%89.5%Claude Opus 4.5
METR time horizonsNot measured75.0%Only Claude Opus 4.5 measured
Remote Labor IndexNot measured3.8%Only Claude Opus 4.5 measured
GDPvalNot measured45.5%Only Claude Opus 4.5 measured
BALROGNot measured43.5%Only Claude Opus 4.5 measured
DeepResearch BenchNot measured54.8%Only Claude Opus 4.5 measured
OSWorldNot measured66.3%Only Claude Opus 4.5 measured
Vending-Bench 2Not measured$4,967Only Claude Opus 4.5 measured
Neither model has a result on the other 27 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Nova Pro 1.0 and Claude Opus 4.5
BenchmarkNova Pro 1.0Claude Opus 4.5Leader
GPQA DiamondNot measured85.9%Only Claude Opus 4.5 measured
MMMU Pro (Vals AI)Not measured83.0%Only Claude Opus 4.5 measured
GPQA Diamond (Artificial Analysis run)49.9%86.6%Claude Opus 4.5
Humanity's Last Exam (Artificial Analysis run)3.2%30.1%Claude Opus 4.5
GPQA Diamond (Epoch AI run)Not measured86.0%Only Claude Opus 4.5 measured
ARC-AGINot measured80.0%Only Claude Opus 4.5 measured
ARC-AGI-2Not measured37.6%Only Claude Opus 4.5 measured
SimpleBenchNot measured62.0%Only Claude Opus 4.5 measured
Chess puzzlesNot measured14.0%Only Claude Opus 4.5 measured
Mystery game puzzlesNot measured22.0%Only Claude Opus 4.5 measured
EBR-benchNot measured14.3%Only Claude Opus 4.5 measured
VPCTNot measured40.0%Only Claude Opus 4.5 measured
LMArena Text: hard prompts12461476Claude Opus 4.5
LMArena Text: expert12111487Claude Opus 4.5
LMArena Text: hard prompts in English12591482Claude Opus 4.5
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index04
Math benchmarks for Nova Pro 1.0 and Claude Opus 4.5
BenchmarkNova Pro 1.0Claude Opus 4.5Leader
AIMENot measured95.4%Only Claude Opus 4.5 measured
MGSM (Vals AI)Not measured95.2%Only Claude Opus 4.5 measured
AA Math Index7.091.3Claude Opus 4.5
AIME 2025 (Artificial Analysis run)7.0%91.3%Claude Opus 4.5
OTIS Mock AIMENot measured86.1%Only Claude Opus 4.5 measured
FrontierMath, tiers 1 to 3Not measured34.4%Only Claude Opus 4.5 measured
FrontierMath, tier 4Not measured4.9%Only Claude Opus 4.5 measured
ProofBenchNot measured36.0%Only Claude Opus 4.5 measured
LMArena Text: math12521463Claude Opus 4.5
LMArena Text: mathematical work12611468Claude Opus 4.5
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for Nova Pro 1.0 and Claude Opus 4.5
BenchmarkNova Pro 1.0Claude Opus 4.5Leader
MMLU ProNot measured87.3%Only Claude Opus 4.5 measured
LegalBench (Vals AI)Not measured84.6%Only Claude Opus 4.5 measured
CaseLaw (Vals AI)Not measured62.6%Only Claude Opus 4.5 measured
CorpFin (Vals AI)Not measured65.1%Only Claude Opus 4.5 measured
TaxEval (Vals AI)Not measured74.9%Only Claude Opus 4.5 measured
MortgageTax (Vals AI)Not measured68.7%Only Claude Opus 4.5 measured
MedQA (Vals AI)Not measured95.9%Only Claude Opus 4.5 measured
MedCode (Vals AI)Not measured49.2%Only Claude Opus 4.5 measured
MMLU Pro (Artificial Analysis run)69.1%89.5%Claude Opus 4.5
SimpleQA VerifiedNot measured45.7%Only Claude Opus 4.5 measured
MMLU82.0%Not measuredOnly Nova Pro 1.0 measured
GeoBenchNot measured75.0%Only Claude Opus 4.5 measured
LMArena Text: science12551454Claude Opus 4.5
LMArena Text: medicine and healthcare12601444Claude Opus 4.5
LMArena Text: legal and government12811459Claude Opus 4.5
LMArena Text: business and finance12291448Claude Opus 4.5
Neither model has a result on the other 1 board here
Web designLike-for-likePublic boards, shown as published, kept out of the index01
Web design benchmarks for Nova Pro 1.0 and Claude Opus 4.5
BenchmarkNova Pro 1.0Claude Opus 4.5Leader
Design Arena: websites7961247Claude Opus 4.5
Design Arena: UI componentsNot measured1238Only Claude Opus 4.5 measured
Design Arena: game devNot measured1229Only Claude Opus 4.5 measured
Design Arena: data vizNot measured1243Only Claude Opus 4.5 measured
Design Arena: 3DNot measured1214Only Claude Opus 4.5 measured
Design Arena: all code categoriesNot measured1242Only Claude Opus 4.5 measured
Design Arena: SVGNot measured1181Only Claude Opus 4.5 measured
Design Arena: ASCII artNot measured1190Only Claude Opus 4.5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index018
General benchmarks for Nova Pro 1.0 and Claude Opus 4.5
BenchmarkNova Pro 1.0Claude Opus 4.5Leader
SAGE (Vals AI)Not measured52.1%Only Claude Opus 4.5 measured
MedScribe (Vals AI)Not measured85.3%Only Claude Opus 4.5 measured
IFBench38.1%58.0%Claude Opus 4.5
Long context reasoning (AA-LCR)21.0%77.3%Claude Opus 4.5
DTBenchNot measured89.9%Only Claude Opus 4.5 measured
LMCANot measured44.5%Only Claude Opus 4.5 measured
CL-benchNot measured21.1%Only Claude Opus 4.5 measured
Furniture assemblyNot measured28.3%Only Claude Opus 4.5 measured
LMArena Text12591451Claude Opus 4.5
LMArena Text: instruction following12351478Claude Opus 4.5
LMArena Text: creative writing12121445Claude Opus 4.5
LMArena Vision980Not measuredOnly Nova Pro 1.0 measured
LMArena Text: English12761461Claude Opus 4.5
LMArena Text: non-English12331438Claude Opus 4.5
LMArena Text: Chinese12441470Claude Opus 4.5
LMArena Text: German12431449Claude Opus 4.5
LMArena Text: Japanese12001417Claude Opus 4.5
LMArena Text: Korean12031424Claude Opus 4.5
LMArena Text: French12711471Claude Opus 4.5
LMArena Text: Spanish11821457Claude Opus 4.5
LMArena Text: Russian12401447Claude Opus 4.5
LMArena Text: PolishNot measured1439Only Claude Opus 4.5 measured
LMArena Text: multi-turn12461466Claude Opus 4.5
LMArena Text: longer queries12551479Claude Opus 4.5
LMArena Text: writing and language12471452Claude Opus 4.5
LMArena Text: entertainment and media12101434Claude Opus 4.5
LMArena Vision: English987Not measuredOnly Nova Pro 1.0 measured
LMArena DocumentNot measured1462Only Claude Opus 4.5 measured
Neither model has a result on the other 18 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 Claude Opus 4.5
BenchmarkNova Pro 1.0Claude Opus 4.5Leader
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
Claude Opus 4.5$0.018Fits in one request

Nova Pro 1.0 costs less

Repository review

50K input + 3K output tokens

Nova Pro 1.0$0.050Fits in one request
Claude Opus 4.5$0.325Fits in one request

Nova Pro 1.0 costs less

Agent loop

200K input + 10K output tokens

Nova Pro 1.0$0.192Fits in one request
Claude Opus 4.5$1.25Exceeds the context window

Nova Pro 1.0 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 Claude Opus 4.5
SpecificationAmazon Nova Pro 1.0Anthropic Claude Opus 4.5
MakerAmazonAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedDecember 5, 2024November 24, 2025
Context window300K200K
Input $/Mtok$0.80$5.00
Output $/Mtok$3.20$25.00
Coding indexNot benchmarked44.0
Independent measurements behind it03
Cost per solved taskNot computable$1.37
SourceOpenRouter listingOpenRouter listing

Questions

Is Nova Pro 1.0 better than Claude Opus 4.5 for coding?

Only Claude Opus 4.5 has a coding score, 44.0 on the Vibe Coding Index; Nova Pro 1.0 has none, so the two cannot be ranked on coding. Pick Nova Pro 1.0 for output tokens 7.8x cheaper ($3.20 vs $25.00 per million) and a larger context window (300K against 200K tokens).

Which is cheaper, Nova Pro 1.0 or Claude Opus 4.5?

Nova Pro 1.0 costs $0.80 per million input tokens and $3.20 per million output tokens; Claude Opus 4.5 costs $5.00 and $25.00. Cost per solved task is known for Claude Opus 4.5 only.

Which has the bigger context window, Nova Pro 1.0 or Claude Opus 4.5?

Nova Pro 1.0, with 300K tokens against 200K.

How many benchmarks is the Nova Pro 1.0 vs Claude Opus 4.5 comparison based on?

39 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 Claude Opus 4.5's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next