Noometry

Model comparison

GPT-4.1 nano vs Llama 3.1 Nemotron Ultra 253b v1

Llama 3.1 Nemotron Ultra 253b v1 is the stronger model overall, scoring 36.7 to 27.9 on the Noometry Index.

Last verified . 11 shared benchmarks.

GPT-4.1 nano OpenAI

27.9

Rank #327 Confirmed

Llama 3.1 Nemotron Ultra 253b v1 NVIDIA

36.7

Rank #213 Confirmed

Summary

  • They share 11 benchmarks with published results for both. GPT-4.1 nano scores higher in 1 category and Llama 3.1 Nemotron Ultra 253b v1 in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Llama 3.1 Nemotron Ultra 253b v1 leads 26.3 to 8.5.
  • The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 33% for GPT-4.1 nano and 10% for Llama 3.1 Nemotron Ultra 253b v1.
  • Llama 3.1 Nemotron Ultra 253b v1 has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 nanoLlama 3.1 Nemotron Ultra 253b v1
ProviderOpenAINVIDIA
Noometry Index27.936.7
Released2025-04-14—
WeightsProprietaryOpen
Context window1.05M—
Max output33K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.40—
Results tracked3811

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

Category by category

Coding Llama 3.1 Nemotron Ultra 253b v1 leads

GPT-4.1 nano: 24.1 (#330), Llama 3.1 Nemotron Ultra 253b v1: 38.4 (#177)

BenchmarkGPT-4.1 nanoLlama 3.1 Nemotron Ultra 253b v1
LMArena Coding13061312
Aider Polyglot8.9%—
SciCode25.9%—
WeirdML19%—

Agentic & Tool Use GPT-4.1 nano leads

GPT-4.1 nano: 26.5 (#104), Llama 3.1 Nemotron Ultra 253b v1: 15.7 (#149)

BenchmarkGPT-4.1 nanoLlama 3.1 Nemotron Ultra 253b v1
Berkeley Function Calling Leaderboard33%10%

Reasoning Llama 3.1 Nemotron Ultra 253b v1 leads

GPT-4.1 nano: 8.5 (#349), Llama 3.1 Nemotron Ultra 253b v1: 26.3 (#134)

BenchmarkGPT-4.1 nanoLlama 3.1 Nemotron Ultra 253b v1
LMArena Hard Prompts12861316
ARC-AGI-20%—
Kagi LLM Benchmark33.3%—
ARC-AGI-10%—
CritPt0%—
DTBench52.5%—
LMCA5.5%—
Epoch Capabilities Index129.62—

Math Llama 3.1 Nemotron Ultra 253b v1 leads

GPT-4.1 nano: 26.9 (#252), Llama 3.1 Nemotron Ultra 253b v1: 37.5 (#152)

BenchmarkGPT-4.1 nanoLlama 3.1 Nemotron Ultra 253b v1
LMArena Math12741360
OTIS Mock AIME 2024-202528.9%—
Omni-MATH36.7%—
MATH Level 570%—
FrontierMath (Feb 2025 set)1%—

Knowledge Not comparable

GPT-4.1 nano: 21.8 (#273), Llama 3.1 Nemotron Ultra 253b v1: —

BenchmarkGPT-4.1 nanoLlama 3.1 Nemotron Ultra 253b v1
GPQA Diamond48.9%—
SimpleQA Verified6%—
MMLU-Pro55%—
GPQA (HELM)50.7%—
LMArena Expert1272—

Multimodal Not comparable

GPT-4.1 nano: 29.2 (#113), Llama 3.1 Nemotron Ultra 253b v1: —

BenchmarkGPT-4.1 nanoLlama 3.1 Nemotron Ultra 253b v1
LMArena Vision1063—

Multilingual Llama 3.1 Nemotron Ultra 253b v1 leads

GPT-4.1 nano: 41.6 (#205), Llama 3.1 Nemotron Ultra 253b v1: 43.1 (#187)

BenchmarkGPT-4.1 nanoLlama 3.1 Nemotron Ultra 253b v1
LMArena Non-English12601282
LMArena Russian12611284
LMArena Chinese1270—
LMArena German1288—
LMArena Japanese1198—

Instruction Following Llama 3.1 Nemotron Ultra 253b v1 leads

GPT-4.1 nano: 67.8 (#193), Llama 3.1 Nemotron Ultra 253b v1: 69.0 (#178)

BenchmarkGPT-4.1 nanoLlama 3.1 Nemotron Ultra 253b v1
LMArena Instruction Following12671308
IFEval84.3%—

Long Context Llama 3.1 Nemotron Ultra 253b v1 leads

GPT-4.1 nano: 23.7 (#296), Llama 3.1 Nemotron Ultra 253b v1: 39.5 (#177)

BenchmarkGPT-4.1 nanoLlama 3.1 Nemotron Ultra 253b v1
LMArena Longer Query12831299
Fiction.LiveBench25%—

Writing & Preference Llama 3.1 Nemotron Ultra 253b v1 leads

GPT-4.1 nano: 40.5 (#243), Llama 3.1 Nemotron Ultra 253b v1: 52.2 (#175)

BenchmarkGPT-4.1 nanoLlama 3.1 Nemotron Ultra 253b v1
LMArena Text12851320
LMArena Creative Writing12601314
LMArena Multi-Turn12771317
EQ-Bench Creative Writing946—
WildBench81.2%—

Frequently asked questions

Is GPT-4.1 nano better than Llama 3.1 Nemotron Ultra 253b v1?

Llama 3.1 Nemotron Ultra 253b v1 is the stronger model overall, scoring 36.7 to 27.9 on the Noometry Index.

Is GPT-4.1 nano or Llama 3.1 Nemotron Ultra 253b v1 better for coding?

Llama 3.1 Nemotron Ultra 253b v1 scores higher on coding benchmarks: 38.4 versus 24.1 in the Noometry coding category.

How many benchmarks do GPT-4.1 nano and Llama 3.1 Nemotron Ultra 253b v1 share?

11 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and Llama 3.1 Nemotron Ultra 253b v1 has 11.

Related comparisons

Go deeper