Enter opens the highlighted result. Esc closes.

Nemotron 3 Nano 30B A3B vs Sonar Pro

Nemotron 3 Nano 30B A3B leads Sonar Pro on the Artificial Analysis Intelligence Index, 8.9 to 7.6, and Nemotron 3 Nano 30B A3B costs 68.2x less per output token ($0.22 vs $15.00 per million). Updated October 22, 2026; 5 benchmarks have a result for both.

Nemotron 3 Nano 30B A3BNVIDIA
Coding
No data
Overall
No data
Output $/M
$0.22
5
Sonar ProPerplexity
Coding
No data
Overall
No data
Output $/M
$15.00
0
vs boards won of 5 shared

Nemotron 3 Nano 30B A3B or Sonar Pro: which to pick

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

Pick Nemotron 3 Nano 30B A3B for output tokens 68.2x cheaper ($0.22 vs $15.00 per million) and a larger context window (262K against 200K tokens).

Shared results
5
Nemotron 3 Nano 30B A3B only
37
Sonar Pro only
0
Like-for-like categories
4 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
Nemotron 3 Nano 30B A3B not benchmarked, Sonar Pro not benchmarked.
Widest category
Coding, 46.6 points apart on average over 1 shared benchmark.
Widest single gap
LiveCodeBench (Artificial Analysis run): Nemotron 3 Nano 30B A3B 74.1% against Sonar Pro 27.5%, 46.6 points apart on a 0 to 100 scale.
Output price
Nemotron 3 Nano 30B A3B $0.22 against Sonar Pro $15.00 per million output tokens, 68.2x apart.
Context window
Nemotron 3 Nano 30B A3B takes 262K tokens, Sonar Pro 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
CategoryNemotron 3 Nano 30B A3BBarsSonar ProTies
Coding10
Intelligence10
Reasoning20
Knowledge10
All shared boards50
CodingLike-for-likeSix of these boards feed the Vibe Coding Index10
Coding benchmarks for Nemotron 3 Nano 30B A3B and Sonar Pro
BenchmarkNemotron 3 Nano 30B A3BSonar ProLeader
AA Coding Index14.4Not measuredOnly Nemotron 3 Nano 30B A3B measured
LiveCodeBench (Artificial Analysis run)74.1%27.5%Nemotron 3 Nano 30B A3B
SciCode30.6%Not measuredOnly Nemotron 3 Nano 30B A3B measured
Terminal-Bench Hard (Artificial Analysis run)13.6%Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: coding1378Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: software and IT1383Not measuredOnly Nemotron 3 Nano 30B A3B measured
Neither model has a result on the other 33 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Nemotron 3 Nano 30B A3B and Sonar Pro
BenchmarkNemotron 3 Nano 30B A3BSonar ProLeader
AA Intelligence Index8.97.6Nemotron 3 Nano 30B A3B
Neither model has a result on the other 1 board here
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Agentic work benchmarks for Nemotron 3 Nano 30B A3B and Sonar Pro
BenchmarkNemotron 3 Nano 30B A3BSonar ProLeader
AA Agentic Index1.0Not measuredOnly Nemotron 3 Nano 30B A3B measured
τ²-Bench Telecom40.9%Not measuredOnly Nemotron 3 Nano 30B A3B measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
Reasoning benchmarks for Nemotron 3 Nano 30B A3B and Sonar Pro
BenchmarkNemotron 3 Nano 30B A3BSonar ProLeader
GPQA Diamond (Artificial Analysis run)75.7%57.8%Nemotron 3 Nano 30B A3B
Humanity's Last Exam (Artificial Analysis run)11.4%6.6%Nemotron 3 Nano 30B A3B
LMArena Text: hard prompts1348Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: expert1355Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: hard prompts in English1376Not measuredOnly Nemotron 3 Nano 30B A3B measured
Neither model has a result on the other 17 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Math benchmarks for Nemotron 3 Nano 30B A3B and Sonar Pro
BenchmarkNemotron 3 Nano 30B A3BSonar ProLeader
AA Math Index91.0Not measuredOnly Nemotron 3 Nano 30B A3B measured
AIME 2025 (Artificial Analysis run)91.0%Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: math1371Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: mathematical work1375Not measuredOnly Nemotron 3 Nano 30B A3B measured
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
Knowledge benchmarks for Nemotron 3 Nano 30B A3B and Sonar Pro
BenchmarkNemotron 3 Nano 30B A3BSonar ProLeader
MMLU Pro (Artificial Analysis run)79.4%75.5%Nemotron 3 Nano 30B A3B
LMArena Text: science1353Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: medicine and healthcare1349Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: legal and government1341Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: business and finance1346Not measuredOnly Nemotron 3 Nano 30B A3B measured
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 Nemotron 3 Nano 30B A3B and Sonar Pro
BenchmarkNemotron 3 Nano 30B A3BSonar ProLeader
Neither model has a result on 9 boards here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index19 boards, none shared
General benchmarks for Nemotron 3 Nano 30B A3B and Sonar Pro
BenchmarkNemotron 3 Nano 30B A3BSonar ProLeader
IFBench71.1%Not measuredOnly Nemotron 3 Nano 30B A3B measured
Long context reasoning (AA-LCR)38.0%Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text1348Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: instruction following1303Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: creative writing1269Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: English1377Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: non-English1320Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: Chinese1383Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: German1348Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: Japanese1268Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: Korean1269Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: French1396Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: Spanish1376Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: Russian1304Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: Polish1303Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: multi-turn1319Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: longer queries1300Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: writing and language1283Not measuredOnly Nemotron 3 Nano 30B A3B measured
LMArena Text: entertainment and media1293Not measuredOnly Nemotron 3 Nano 30B A3B measured
Neither model has a result on the other 27 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Nemotron 3 Nano 30B A3B and Sonar Pro
BenchmarkNemotron 3 Nano 30B A3BSonar ProLeader
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

Nemotron 3 Nano 30B A3B$0.0002Fits in one request
Sonar Pro$0.011Fits in one request

Nemotron 3 Nano 30B A3B costs less

Repository review

50K input + 3K output tokens

Nemotron 3 Nano 30B A3B$0.0034Fits in one request
Sonar Pro$0.195Fits in one request

Nemotron 3 Nano 30B A3B costs less

Agent loop

200K input + 10K output tokens

Nemotron 3 Nano 30B A3B$0.013Fits in one request
Sonar Pro$0.750Exceeds the context window

Nemotron 3 Nano 30B A3B 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 Nemotron 3 Nano 30B A3B and Sonar Pro
SpecificationNVIDIA Nemotron 3 Nano 30B A3BPerplexity Sonar Pro
MakerNVIDIAPerplexity
WeightsOpen weightsNo public weights listed
ReleasedDecember 14, 2025March 7, 2025
Context window262K200K
Input $/Mtok$0.055$3.00
Output $/Mtok$0.22$15.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Nemotron 3 Nano 30B A3B better than Sonar Pro for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Nemotron 3 Nano 30B A3B for output tokens 68.2x cheaper ($0.22 vs $15.00 per million) and a larger context window (262K against 200K tokens).

Which is cheaper, Nemotron 3 Nano 30B A3B or Sonar Pro?

Nemotron 3 Nano 30B A3B costs $0.055 per million input tokens and $0.22 per million output tokens; Sonar Pro costs $3.00 and $15.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Nemotron 3 Nano 30B A3B or Sonar Pro?

Nemotron 3 Nano 30B A3B, with 262K tokens against 200K.

How many benchmarks is the Nemotron 3 Nano 30B A3B vs Sonar Pro comparison based on?

5 benchmarks have a result for both models as of October 22, 2026. Nemotron 3 Nano 30B A3B's coding index rests on 0 independent benchmarks and Sonar Pro's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next