Noometry

Model comparison

GPT-4 vs Nemotron 3 Ultra

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 29.1 on the Noometry Index.

Last verified . 25 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Nemotron 3 Ultra NVIDIA

42.5

Rank #113 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Nemotron 3 Ultra in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 18.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for GPT-4 and 86.7% for Nemotron 3 Ultra.
  • Nemotron 3 Ultra is cheaper at $0.50 / $2.20 per million input/output tokens, against $30 / $60 for GPT-4.
  • Nemotron 3 Ultra accepts more context: 262K tokens versus 8K.
  • Nemotron 3 Ultra has downloadable open weights; the other is API-only.

Side by side

GPT-4Nemotron 3 Ultra
ProviderOpenAINVIDIA
Noometry Index29.142.5
Released2023-03-142026-06-04
WeightsProprietaryOpen
Context window8K262K
Max output8K128K
Input $ / M tokens$30$0.50
Output $ / M tokens$60$2.20
Results tracked3830

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Nemotron 3 Ultra leads

GPT-4: 31.6 (#283), Nemotron 3 Ultra: 38.1 (#182)

BenchmarkGPT-4Nemotron 3 Ultra
WeirdML12.4%43.5%
LMArena Coding12541468
FrontierCode—13.6%
SciCode—40.3%
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Nemotron 3 Ultra: 23.4 (#126)

BenchmarkGPT-4Nemotron 3 Ultra
APEX-Agents—22.7%
METR Time Horizons36.1%—

Reasoning Nemotron 3 Ultra leads

GPT-4: 17.8 (#289), Nemotron 3 Ultra: 31.0 (#82)

BenchmarkGPT-4Nemotron 3 Ultra
Chess Puzzles4%12%
LMArena Hard Prompts12411452
Mystery Game Puzzles12%20%
DTBench62.7%90.1%
LMCA17.1%36.9%
Epoch Capabilities Index125.89146.17
CritPt—3.1%
BIG-Bench Hard75.1%—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Nemotron 3 Ultra leads

GPT-4: 10.8 (#309), Nemotron 3 Ultra: 35.3 (#187)

BenchmarkGPT-4Nemotron 3 Ultra
OTIS Mock AIME 2024-20251.1%86.7%
LMArena Math12691457
ProofBench—2%
MATH Level 523%—
GSM8K92%—

Knowledge Nemotron 3 Ultra leads

GPT-4: 18.4 (#282), Nemotron 3 Ultra: 52.5 (#61)

BenchmarkGPT-4Nemotron 3 Ultra
GPQA Diamond35.7%85.4%
LMArena Expert12111472
MMLU86.4%—
TriviaQA84.8%—

Multilingual Nemotron 3 Ultra leads

GPT-4: 40.6 (#215), Nemotron 3 Ultra: 53.5 (#64)

BenchmarkGPT-4Nemotron 3 Ultra
LMArena Non-English12461427
LMArena Chinese12421497
LMArena French12831472
LMArena German12511471
LMArena Korean11841386
LMArena Russian12511417
LMArena Spanish12611454
LMArena Japanese1209—

Instruction Following Nemotron 3 Ultra leads

GPT-4: 65.3 (#222), Nemotron 3 Ultra: 74.7 (#88)

BenchmarkGPT-4Nemotron 3 Ultra
LMArena Instruction Following12411418

Long Context Nemotron 3 Ultra leads

GPT-4: 37.7 (#212), Nemotron 3 Ultra: 43.9 (#81)

BenchmarkGPT-4Nemotron 3 Ultra
LMArena Longer Query12441437

Writing & Preference Nemotron 3 Ultra leads

GPT-4: 34.9 (#268), Nemotron 3 Ultra: 66.3 (#36)

BenchmarkGPT-4Nemotron 3 Ultra
LMArena Text12631445
LMArena Creative Writing12441398
EQ-Bench Creative Writing7521692
LMArena Multi-Turn12571411

Frequently asked questions

Is GPT-4 better than Nemotron 3 Ultra?

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or Nemotron 3 Ultra?

Nemotron 3 Ultra is cheaper. It lists at $0.50 per million input tokens and $2.20 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or Nemotron 3 Ultra better for coding?

Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Nemotron 3 Ultra does, with 262K tokens against 8K.

How many benchmarks do GPT-4 and Nemotron 3 Ultra share?

25 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Nemotron 3 Ultra has 30.

Related comparisons

Go deeper