Enter opens the highlighted result. Esc closes.

Nova Pro 1.0 vs Llama 3.3 70B Instruct

Llama 3.3 70B Instruct leads Nova Pro 1.0 on the Artificial Analysis Intelligence Index, 7.7 to 7.0, and Llama 3.3 70B Instruct costs 4.4x less per output token ($0.72 vs $3.20 per million). Updated October 21, 2026; 39 benchmarks have a result for both.

Replace Nova Pro 1.0 Replace Llama 3.3 70B Instruct
Nova Pro 1.0Amazon
Coding
No data
Overall
No data
Output $/M
$3.20
7
Llama 3.3 70B InstructMeta Llama
Coding
No data
Overall
26.0
Output $/M
$0.72
32
vs boards won of 39 shared

Nova Pro 1.0 or Llama 3.3 70B 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 131K tokens) and work measured by LiveCodeBench (Artificial Analysis run) or LMArena Text: software and IT, where it leads.

Model ANova Pro 1.0AmazonNot benchmarkedNo coding benchmarkNo cost per solved taskModel BLlama 3.3 70B InstructMeta LlamaNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
39
Nova Pro 1.0 only
3
Llama 3.3 70B Instruct only
13
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, Llama 3.3 70B Instruct not benchmarked.
Widest category
Agentic work, 12.6 points apart on average over 1 shared benchmark.
Widest single gap
LMArena Text: Spanish: Nova Pro 1.0 1182 against Llama 3.3 70B Instruct 1269, 14.6 points apart on a 0 to 100 scale.
Output price
Nova Pro 1.0 $3.20 against Llama 3.3 70B Instruct $0.72 per million output tokens, 4.4x apart.
Context window
Nova Pro 1.0 takes 300K tokens, Llama 3.3 70B Instruct 131K.

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 1.0BarsLlama 3.3 70B InstructTies
Coding22
Intelligence01
Agentic work01
Reasoning14
Math04
Knowledge06
General414
All shared boards732
CodingLike-for-likeSix of these boards feed the Vibe Coding Index22
Coding benchmarks for Nova Pro 1.0 and Llama 3.3 70B Instruct
BenchmarkNova Pro 1.0Llama 3.3 70B InstructLeader
AA Coding IndexNot measured11.9Only Llama 3.3 70B Instruct measured
LiveCodeBench (Artificial Analysis run)23.3%28.8%Llama 3.3 70B Instruct
Terminal-Bench Hard (Artificial Analysis run)6.1%3.0%Nova Pro 1.0
WeirdMLNot measured14.4%Only Llama 3.3 70B Instruct measured
LMArena Text: coding12701268Nova Pro 1.0
LMArena Text: software and IT12711273Llama 3.3 70B 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 Llama 3.3 70B Instruct
BenchmarkNova Pro 1.0Llama 3.3 70B InstructLeader
AA Intelligence Index7.07.7Llama 3.3 70B Instruct
Epoch Capabilities IndexNot measured127.3Only Llama 3.3 70B Instruct measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Nova Pro 1.0 and Llama 3.3 70B Instruct
BenchmarkNova Pro 1.0Llama 3.3 70B InstructLeader
τ²-Bench Telecom14.0%26.6%Llama 3.3 70B Instruct
BALROGNot measured23.0%Only Llama 3.3 70B Instruct measured
Berkeley Function Calling Leaderboard (BFCL)Not measured31.9%Only Llama 3.3 70B Instruct measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index14
Reasoning benchmarks for Nova Pro 1.0 and Llama 3.3 70B Instruct
BenchmarkNova Pro 1.0Llama 3.3 70B InstructLeader
GPQA Diamond (Artificial Analysis run)49.9%49.8%Nova Pro 1.0
Humanity's Last Exam (Artificial Analysis run)3.2%3.6%Llama 3.3 70B Instruct
GPQA Diamond (Epoch AI run)Not measured47.4%Only Llama 3.3 70B Instruct measured
SimpleBenchNot measured19.9%Only Llama 3.3 70B Instruct measured
LMArena Text: hard prompts12461257Llama 3.3 70B Instruct
LMArena Text: expert12111225Llama 3.3 70B Instruct
LMArena Text: hard prompts in English12591277Llama 3.3 70B Instruct
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index04
Math benchmarks for Nova Pro 1.0 and Llama 3.3 70B Instruct
BenchmarkNova Pro 1.0Llama 3.3 70B InstructLeader
AA Math Index7.07.7Llama 3.3 70B Instruct
AIME 2025 (Artificial Analysis run)7.0%7.7%Llama 3.3 70B Instruct
OTIS Mock AIMENot measured5.1%Only Llama 3.3 70B Instruct measured
MATH level 5Not measured41.6%Only Llama 3.3 70B Instruct measured
LMArena Text: math12521267Llama 3.3 70B Instruct
LMArena Text: mathematical work12611267Llama 3.3 70B Instruct
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index06
Knowledge benchmarks for Nova Pro 1.0 and Llama 3.3 70B Instruct
BenchmarkNova Pro 1.0Llama 3.3 70B InstructLeader
MMLU Pro (Artificial Analysis run)69.1%71.3%Llama 3.3 70B Instruct
MMLU82.0%86.3%Llama 3.3 70B Instruct
LMArena Text: science12551284Llama 3.3 70B Instruct
LMArena Text: medicine and healthcare12601275Llama 3.3 70B Instruct
LMArena Text: legal and government12811284Llama 3.3 70B Instruct
LMArena Text: business and finance12291243Llama 3.3 70B Instruct
Neither model has a result on the other 12 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 Llama 3.3 70B Instruct
BenchmarkNova Pro 1.0Llama 3.3 70B 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 index414
General benchmarks for Nova Pro 1.0 and Llama 3.3 70B Instruct
BenchmarkNova Pro 1.0Llama 3.3 70B InstructLeader
IFBench38.1%47.1%Llama 3.3 70B Instruct
Long context reasoning (AA-LCR)21.0%15.7%Nova Pro 1.0
DTBenchNot measured59.5%Only Llama 3.3 70B Instruct measured
LMCANot measured17.5%Only Llama 3.3 70B Instruct measured
Fiction.LiveBenchNot measured33.3%Only Llama 3.3 70B Instruct measured
LMArena Text12591274Llama 3.3 70B Instruct
LMArena Text: instruction following12351242Llama 3.3 70B Instruct
LMArena Text: creative writing12121250Llama 3.3 70B Instruct
LMArena Vision980Not measuredOnly Nova Pro 1.0 measured
LMArena Text: English12761303Llama 3.3 70B Instruct
LMArena Text: non-English12331236Llama 3.3 70B Instruct
LMArena Text: Chinese12441217Nova Pro 1.0
LMArena Text: German12431251Llama 3.3 70B Instruct
LMArena Text: Japanese12001150Nova Pro 1.0
LMArena Text: Korean12031142Nova Pro 1.0
LMArena Text: French12711282Llama 3.3 70B Instruct
LMArena Text: Spanish11821269Llama 3.3 70B Instruct
LMArena Text: Russian12401252Llama 3.3 70B Instruct
LMArena Text: PolishNot measured1259Only Llama 3.3 70B Instruct measured
LMArena Text: multi-turn12461280Llama 3.3 70B Instruct
LMArena Text: longer queries12551255Llama 3.3 70B Instruct
LMArena Text: writing and language12471255Llama 3.3 70B Instruct
LMArena Text: entertainment and media12101241Llama 3.3 70B Instruct
LMArena Vision: English987Not measuredOnly Nova Pro 1.0 measured
Neither model has a result on the other 22 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 Llama 3.3 70B Instruct
BenchmarkNova Pro 1.0Llama 3.3 70B 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
Llama 3.3 70B Instruct$0.0008Fits in one request

Llama 3.3 70B Instruct costs less

Repository review

50K input + 3K output tokens

Nova Pro 1.0$0.050Fits in one request
Llama 3.3 70B Instruct$0.025Fits in one request

Llama 3.3 70B Instruct costs less

Agent loop

200K input + 10K output tokens

Nova Pro 1.0$0.192Fits in one request
Llama 3.3 70B Instruct$0.097Exceeds the context window

Llama 3.3 70B 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 Llama 3.3 70B Instruct
SpecificationAmazon Nova Pro 1.0Meta Llama 3.3 70B Instruct
MakerAmazonMeta Llama
WeightsNo public weights listedOpen weights
ReleasedDecember 5, 2024December 6, 2024
Context window300K131K
Input $/Mtok$0.80$0.45
Output $/Mtok$3.20$0.72
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 Llama 3.3 70B 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 131K tokens) and work measured by LiveCodeBench (Artificial Analysis run) or LMArena Text: software and IT, where it leads.

Which is cheaper, Nova Pro 1.0 or Llama 3.3 70B Instruct?

Nova Pro 1.0 costs $0.80 per million input tokens and $3.20 per million output tokens; Llama 3.3 70B Instruct costs $0.45 and $0.72. Cost per solved task is known for neither of them.

Which has the bigger context window, Nova Pro 1.0 or Llama 3.3 70B Instruct?

Nova Pro 1.0, with 300K tokens against 131K.

How many benchmarks is the Nova Pro 1.0 vs Llama 3.3 70B Instruct 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 Llama 3.3 70B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next