Noometry

Model comparison

GPT-4.5 vs Nemotron 3 Ultra

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 37.2 on the Noometry Index.

Last verified . 20 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Nemotron 3 Ultra NVIDIA

42.5

Rank #113 Confirmed

Summary

  • They share 20 benchmarks with published results for both. GPT-4.5 scores higher in 2 categories and Nemotron 3 Ultra in 7 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 32.5.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for GPT-4.5 and 86.7% for Nemotron 3 Ultra.
  • Nemotron 3 Ultra has downloadable open weights; the other is API-only.

Side by side

GPT-4.5Nemotron 3 Ultra
ProviderOpenAINVIDIA
Noometry Index37.242.5
Released2025-02-272026-06-04
WeightsProprietaryOpen
Context window—262K
Max output—128K
Input $ / M tokens—$0.60
Output $ / M tokens—$2.40
Results tracked4230

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

Category by category

Coding GPT-4.5 leads

GPT-4.5: 42.2 (#109), Nemotron 3 Ultra: 38.1 (#182)

BenchmarkGPT-4.5Nemotron 3 Ultra
WeirdML39.4%43.5%
LMArena Coding13961468
FrontierCode—13.6%
Aider Polyglot44.9%—
SciCode—40.3%
LiveBench Coding75.2%—

Agentic & Tool Use GPT-4.5 leads

GPT-4.5: 27.9 (#97), Nemotron 3 Ultra: 23.4 (#126)

BenchmarkGPT-4.5Nemotron 3 Ultra
APEX-Agents—22.7%
Cybench17.5%—

Reasoning Nemotron 3 Ultra leads

GPT-4.5: 13.9 (#330), Nemotron 3 Ultra: 31.0 (#82)

BenchmarkGPT-4.5Nemotron 3 Ultra
LMArena Hard Prompts14031452
Epoch Capabilities Index136.74146.17
ARC-AGI-20.8%—
SimpleBench34.5%—
ARC-AGI-110.3%—
CritPt—3.1%
Chess Puzzles—12%
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
Mystery Game Puzzles—20%
DTBench—90.1%
LiveBench Data Analysis64.3%—
LMCA—36.9%
ForecastBench61.7—
LiveBench69%—

Math Nemotron 3 Ultra leads

GPT-4.5: 32.6 (#211), Nemotron 3 Ultra: 35.3 (#187)

BenchmarkGPT-4.5Nemotron 3 Ultra
OTIS Mock AIME 2024-202537.8%86.7%
LMArena Math14121457
ProofBench—2%
LiveBench Math69.3%—
MATH Level 578.6%—

Knowledge Nemotron 3 Ultra leads

GPT-4.5: 32.5 (#211), Nemotron 3 Ultra: 52.5 (#61)

BenchmarkGPT-4.5Nemotron 3 Ultra
GPQA Diamond68.7%85.4%
LMArena Expert13941472
Humanity's Last Exam5.4%—
Confabulations13.6%—

Multimodal Not comparable

GPT-4.5: 37.6 (#71), Nemotron 3 Ultra: —

BenchmarkGPT-4.5Nemotron 3 Ultra
LMArena Vision1195—
VPCT45%—

Multilingual Nemotron 3 Ultra leads

GPT-4.5: 52.5 (#83), Nemotron 3 Ultra: 53.5 (#64)

BenchmarkGPT-4.5Nemotron 3 Ultra
LMArena Non-English14131427
LMArena Chinese14211497
LMArena French14181472
LMArena German14571471
LMArena Korean13921386
LMArena Russian14191417
LMArena Japanese1416—
LMArena Spanish—1454

Instruction Following Nemotron 3 Ultra leads

GPT-4.5: 72.6 (#134), Nemotron 3 Ultra: 74.7 (#88)

BenchmarkGPT-4.5Nemotron 3 Ultra
LMArena Instruction Following14041418
LiveBench Instruction Following72.3%—

Long Context Nemotron 3 Ultra leads

GPT-4.5: 40.4 (#155), Nemotron 3 Ultra: 43.9 (#81)

BenchmarkGPT-4.5Nemotron 3 Ultra
LMArena Longer Query14061437
Fiction.LiveBench63.9%—

Writing & Preference Nemotron 3 Ultra leads

GPT-4.5: 56.9 (#134), Nemotron 3 Ultra: 66.3 (#36)

BenchmarkGPT-4.5Nemotron 3 Ultra
LMArena Text14171445
LMArena Creative Writing13941398
EQ-Bench Creative Writing12581692
LMArena Multi-Turn14441411
Short-Story Creative Writing75.6%—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Nemotron 3 Ultra?

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 37.2 on the Noometry Index.

Is GPT-4.5 or Nemotron 3 Ultra better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 38.1 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Nemotron 3 Ultra share?

20 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Nemotron 3 Ultra has 30.

Related comparisons

Go deeper