Enter opens the highlighted result. Esc closes.

GPT-4o (2024-05-13) vs Nemotron 3 Super

Nemotron 3 Super leads GPT-4o (2024-05-13) on the Artificial Analysis Intelligence Index, 12.8 to 7.3, and Nemotron 3 Super costs 33.3x less per output token ($0.45 vs $15.00 per million). Updated October 23, 2026; 30 benchmarks have a result for both.

Replace GPT-4o (2024-05-13) Replace Nemotron 3 Super
GPT-4o (2024-05-13)OpenAI
Coding
No data
Overall
27.1
Output $/M
$15.00
1
Nemotron 3 SuperNVIDIA
Coding
No data
Overall
No data
Output $/M
$0.45
29
vs boards won of 30 shared

GPT-4o (2024-05-13) or Nemotron 3 Super: which to pick

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

Pick GPT-4o (2024-05-13) for work measured by AA Coding Index or LMArena Text: coding, where it leads.

Model AGPT-4o (2024-05-13)OpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BNemotron 3 SuperNVIDIANot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
30
GPT-4o (2024-05-13) only
14
Nemotron 3 Super only
9
Like-for-like categories
6 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
GPT-4o (2024-05-13) not benchmarked, Nemotron 3 Super not benchmarked.
Widest category
Reasoning, 21.2 points apart on average over 5 shared benchmarks.
Widest single gap
GPQA Diamond (Artificial Analysis run): GPT-4o (2024-05-13) 52.6% against Nemotron 3 Super 80.0%, 27.4 points apart on a 0 to 100 scale.
Output price
GPT-4o (2024-05-13) $15.00 against Nemotron 3 Super $0.45 per million output tokens, 33.3x apart.
Context window
GPT-4o (2024-05-13) takes 128K tokens, Nemotron 3 Super 262K.

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
CategoryGPT-4o (2024-05-13)BarsNemotron 3 SuperTies
Coding03
Intelligence01
Reasoning05
Math02
Knowledge04
General114
All shared boards129
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for GPT-4o (2024-05-13) and Nemotron 3 Super
BenchmarkGPT-4o (2024-05-13)Nemotron 3 SuperLeader
AA Coding Index24.237.7Nemotron 3 Super
LiveCodeBench (Artificial Analysis run)33.4%Not measuredOnly GPT-4o (2024-05-13) measured
SciCodeNot measured36.2%Only Nemotron 3 Super measured
Terminal-Bench Hard (Artificial Analysis run)Not measured28.8%Only Nemotron 3 Super measured
WeirdMLNot measured38.0%Only Nemotron 3 Super measured
ALE-BenchNot measured213.9Only Nemotron 3 Super measured
LMArena Text: coding12971404Nemotron 3 Super
LMArena Text: software and IT12971409Nemotron 3 Super
Neither model has a result on the other 35 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for GPT-4o (2024-05-13) and Nemotron 3 Super
BenchmarkGPT-4o (2024-05-13)Nemotron 3 SuperLeader
AA Intelligence Index7.312.8Nemotron 3 Super
Neither model has a result on the other 1 board here
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Agentic work benchmarks for GPT-4o (2024-05-13) and Nemotron 3 Super
BenchmarkGPT-4o (2024-05-13)Nemotron 3 SuperLeader
AA Agentic IndexNot measured1.7Only Nemotron 3 Super measured
τ²-Bench TelecomNot measured67.8%Only Nemotron 3 Super measured
METR time horizons40.8%Not measuredOnly GPT-4o (2024-05-13) measured
BALROG32.3%Not measuredOnly GPT-4o (2024-05-13) measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for GPT-4o (2024-05-13) and Nemotron 3 Super
BenchmarkGPT-4o (2024-05-13)Nemotron 3 SuperLeader
GPQA Diamond50.2%Not measuredOnly GPT-4o (2024-05-13) measured
GPQA Diamond (Artificial Analysis run)52.6%80.0%Nemotron 3 Super
Humanity's Last Exam (Artificial Analysis run)1.8%20.8%Nemotron 3 Super
GPQA Diamond (Epoch AI run)48.9%Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: hard prompts12811386Nemotron 3 Super
LMArena Text: expert12501398Nemotron 3 Super
LMArena Text: hard prompts in English12931397Nemotron 3 Super
Neither model has a result on the other 16 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for GPT-4o (2024-05-13) and Nemotron 3 Super
BenchmarkGPT-4o (2024-05-13)Nemotron 3 SuperLeader
OTIS Mock AIME6.3%Not measuredOnly GPT-4o (2024-05-13) measured
MATH level 551.0%Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: math12841380Nemotron 3 Super
LMArena Text: mathematical work12841405Nemotron 3 Super
MathArenaNot measured16.6%Only Nemotron 3 Super measured
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for GPT-4o (2024-05-13) and Nemotron 3 Super
BenchmarkGPT-4o (2024-05-13)Nemotron 3 SuperLeader
MMLU Pro (Artificial Analysis run)74.0%Not measuredOnly GPT-4o (2024-05-13) measured
MMLU84.2%Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: science12951388Nemotron 3 Super
LMArena Text: medicine and healthcare12781383Nemotron 3 Super
LMArena Text: legal and government13141392Nemotron 3 Super
LMArena Text: business and finance12611364Nemotron 3 Super
Neither model has a result on the other 14 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for GPT-4o (2024-05-13) and Nemotron 3 Super
BenchmarkGPT-4o (2024-05-13)Nemotron 3 SuperLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index114
General benchmarks for GPT-4o (2024-05-13) and Nemotron 3 Super
BenchmarkGPT-4o (2024-05-13)Nemotron 3 SuperLeader
IFBenchNot measured71.5%Only Nemotron 3 Super measured
Long context reasoning (AA-LCR)Not measured65.7%Only Nemotron 3 Super measured
LMArena Text13001378Nemotron 3 Super
LMArena Text: instruction following12781347Nemotron 3 Super
LMArena Text: creative writing12911317Nemotron 3 Super
LMArena Vision1137Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: English13121400Nemotron 3 Super
LMArena Text: non-English12831356Nemotron 3 Super
LMArena Text: Chinese12771432Nemotron 3 Super
LMArena Text: German12821341Nemotron 3 Super
LMArena Text: Japanese1257Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: Korean1234Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Text: French13041403Nemotron 3 Super
LMArena Text: Spanish12921418Nemotron 3 Super
LMArena Text: Russian12851336Nemotron 3 Super
LMArena Text: Polish13651346GPT-4o (2024-05-13)
LMArena Text: multi-turn13021369Nemotron 3 Super
LMArena Text: longer queries12881362Nemotron 3 Super
LMArena Text: writing and language12981331Nemotron 3 Super
LMArena Text: entertainment and media12891336Nemotron 3 Super
LMArena Vision: English1147Not measuredOnly GPT-4o (2024-05-13) measured
LMArena Vision: Chinese1132Not measuredOnly GPT-4o (2024-05-13) measured
Neither model has a result on the other 26 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4o (2024-05-13) and Nemotron 3 Super
BenchmarkGPT-4o (2024-05-13)Nemotron 3 SuperLeader
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

GPT-4o (2024-05-13)$0.013Fits in one request
Nemotron 3 Super$0.0003Fits in one request

Nemotron 3 Super costs less

Repository review

50K input + 3K output tokens

GPT-4o (2024-05-13)$0.295Fits in one request
Nemotron 3 Super$0.0056Fits in one request

Nemotron 3 Super costs less

Agent loop

200K input + 10K output tokens

GPT-4o (2024-05-13)$1.15Exceeds the context window
Nemotron 3 Super$0.021Fits in one request

Nemotron 3 Super 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 GPT-4o (2024-05-13) and Nemotron 3 Super
SpecificationOpenAI GPT-4o (2024-05-13)NVIDIA Nemotron 3 Super
MakerOpenAINVIDIA
WeightsNo public weights listedOpen weights
ReleasedMay 13, 2024March 11, 2026
Context window128K262K
Input $/Mtok$5.00$0.085
Output $/Mtok$15.00$0.45
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4o (2024-05-13) better than Nemotron 3 Super for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4o (2024-05-13) for work measured by AA Coding Index or LMArena Text: coding, where it leads.

Which is cheaper, GPT-4o (2024-05-13) or Nemotron 3 Super?

GPT-4o (2024-05-13) costs $5.00 per million input tokens and $15.00 per million output tokens; Nemotron 3 Super costs $0.085 and $0.45. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-4o (2024-05-13) or Nemotron 3 Super?

Nemotron 3 Super, with 262K tokens against 128K.

How many benchmarks is the GPT-4o (2024-05-13) vs Nemotron 3 Super comparison based on?

30 benchmarks have a result for both models as of October 23, 2026. GPT-4o (2024-05-13)'s coding index rests on 0 independent benchmarks and Nemotron 3 Super's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next