Noometry

Model comparison

GPT-4.1 mini vs Nemotron 3 Ultra

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 33.6 on the Noometry Index.

Last verified . 27 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

Nemotron 3 Ultra NVIDIA

42.5

Rank #113 Confirmed

Summary

  • They share 27 benchmarks with published results for both. GPT-4.1 mini scores higher in 1 category and Nemotron 3 Ultra in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Nemotron 3 Ultra leads 31.0 to 10.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 44.7% for GPT-4.1 mini and 86.7% for Nemotron 3 Ultra.
  • GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $0.60 / $2.40 for Nemotron 3 Ultra.
  • GPT-4.1 mini accepts more context: 1.05M tokens versus 262K.
  • Nemotron 3 Ultra has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 miniNemotron 3 Ultra
ProviderOpenAINVIDIA
Noometry Index33.642.5
Released2025-04-142026-06-04
WeightsProprietaryOpen
Context window1.05M262K
Max output33K128K
Input $ / M tokens$0.40$0.60
Output $ / M tokens$1.60$2.40
Results tracked4730

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

Category by category

Coding Nemotron 3 Ultra leads

GPT-4.1 mini: 30.6 (#293), Nemotron 3 Ultra: 38.1 (#182)

BenchmarkGPT-4.1 miniNemotron 3 Ultra
SciCode40.4%40.3%
WeirdML37.6%43.5%
LMArena Coding13671468
FrontierCode—13.6%
SWE-bench Verified (bash only)23.9%—
Aider Polyglot32.4%—
BigCodeBench Instruct48.9%—
CadEval16%—

Agentic & Tool Use GPT-4.1 mini leads

GPT-4.1 mini: 33.3 (#55), Nemotron 3 Ultra: 23.4 (#126)

BenchmarkGPT-4.1 miniNemotron 3 Ultra
APEX-Agents—22.7%
Berkeley Function Calling Leaderboard50.5%—

Reasoning Nemotron 3 Ultra leads

GPT-4.1 mini: 10.8 (#340), Nemotron 3 Ultra: 31.0 (#82)

BenchmarkGPT-4.1 miniNemotron 3 Ultra
CritPt0%3.1%
Chess Puzzles7%12%
LMArena Hard Prompts13491452
Mystery Game Puzzles7%20%
DTBench68.8%90.1%
LMCA21.1%36.9%
Epoch Capabilities Index135.01146.17
ARC-AGI-20%—
Kagi LLM Benchmark48.6%—
ARC-AGI-13.5%—

Math Nemotron 3 Ultra leads

GPT-4.1 mini: 24.1 (#270), Nemotron 3 Ultra: 35.3 (#187)

BenchmarkGPT-4.1 miniNemotron 3 Ultra
OTIS Mock AIME 2024-202544.7%86.7%
LMArena Math13431457
FrontierMath (Tiers 1-3)6.7%—
ProofBench—2%
Omni-MATH49.1%—
MATH Level 587.3%—
FrontierMath (Feb 2025 set)4.5%—

Knowledge Nemotron 3 Ultra leads

GPT-4.1 mini: 34.7 (#194), Nemotron 3 Ultra: 52.5 (#61)

BenchmarkGPT-4.1 miniNemotron 3 Ultra
GPQA Diamond65.8%85.4%
LMArena Expert13381472
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
GPQA (HELM)61.4%—

Multimodal Not comparable

GPT-4.1 mini: 35.8 (#82), Nemotron 3 Ultra: —

BenchmarkGPT-4.1 miniNemotron 3 Ultra
LMArena Vision1181—

Multilingual Nemotron 3 Ultra leads

GPT-4.1 mini: 45.7 (#166), Nemotron 3 Ultra: 53.5 (#64)

BenchmarkGPT-4.1 miniNemotron 3 Ultra
LMArena Non-English13181427
LMArena Chinese13291497
LMArena French13581472
LMArena German13511471
LMArena Korean12981386
LMArena Russian13241417
LMArena Spanish13191454
LMArena Japanese1290—

Instruction Following Nemotron 3 Ultra leads

GPT-4.1 mini: 73.7 (#118), Nemotron 3 Ultra: 74.7 (#88)

BenchmarkGPT-4.1 miniNemotron 3 Ultra
LMArena Instruction Following13331418
IFEval90.4%—

Long Context Nemotron 3 Ultra leads

GPT-4.1 mini: 31.8 (#275), Nemotron 3 Ultra: 43.9 (#81)

BenchmarkGPT-4.1 miniNemotron 3 Ultra
LMArena Longer Query13441437
Fiction.LiveBench44.4%—

Writing & Preference Nemotron 3 Ultra leads

GPT-4.1 mini: 48.6 (#199), Nemotron 3 Ultra: 66.3 (#36)

BenchmarkGPT-4.1 miniNemotron 3 Ultra
LMArena Text13401445
LMArena Creative Writing13001398
EQ-Bench Creative Writing11471692
LMArena Multi-Turn13541411
WildBench83.8%—

Frequently asked questions

Is GPT-4.1 mini better than Nemotron 3 Ultra?

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 33.6 on the Noometry Index.

Which is cheaper, GPT-4.1 mini or Nemotron 3 Ultra?

GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Nemotron 3 Ultra lists at $0.60 and $2.40.

Is GPT-4.1 mini or Nemotron 3 Ultra better for coding?

Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 30.6 in the Noometry coding category.

Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 262K.

How many benchmarks do GPT-4.1 mini and Nemotron 3 Ultra share?

27 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Nemotron 3 Ultra has 30.

Related comparisons

Go deeper