Noometry

Model comparison

Llama 3.1 Nemotron Ultra 253b v1 vs Nvidia Llama 3.3 Nemotron Super 49b v1.5

Nvidia Llama 3.3 Nemotron Super 49b v1.5 is the stronger model overall, scoring 40.3 to 36.7 on the Noometry Index.

Last verified . 10 shared benchmarks.

Llama 3.1 Nemotron Ultra 253b v1 NVIDIA

36.7

Rank #213 Confirmed

Nvidia Llama 3.3 Nemotron Super 49b v1.5 NVIDIA

40.3

Rank #151 Confirmed

Summary

  • They share 10 benchmarks with published results for both. Llama 3.1 Nemotron Ultra 253b v1 scores higher in 1 category and Nvidia Llama 3.3 Nemotron Super 49b v1.5 in 6 categories; 2 gaps are clear of the uncertainty.

Side by side

Llama 3.1 Nemotron Ultra 253b v1Nvidia Llama 3.3 Nemotron Super 49b v1.5
ProviderNVIDIANVIDIA
Noometry Index36.740.3
Released—2025-07-25
WeightsOpenOpen
Context window—131K
Max output—131K
Input $ / M tokens—$0.40
Output $ / M tokens—$0.40
Results tracked1112

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

Category by category

Coding Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads

Llama 3.1 Nemotron Ultra 253b v1: 38.4 (#177), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 39.8 (#154)

BenchmarkLlama 3.1 Nemotron Ultra 253b v1Nvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Coding13121355

Agentic & Tool Use Not comparable

Llama 3.1 Nemotron Ultra 253b v1: 15.7 (#149), Nvidia Llama 3.3 Nemotron Super 49b v1.5: —

BenchmarkLlama 3.1 Nemotron Ultra 253b v1Nvidia Llama 3.3 Nemotron Super 49b v1.5
Berkeley Function Calling Leaderboard10%—

Reasoning Too close to call

Llama 3.1 Nemotron Ultra 253b v1: 26.3 (#134), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 26.8 (#128)

BenchmarkLlama 3.1 Nemotron Ultra 253b v1Nvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Hard Prompts13161336

Math Too close to call

Llama 3.1 Nemotron Ultra 253b v1: 37.5 (#152), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 38.2 (#141)

BenchmarkLlama 3.1 Nemotron Ultra 253b v1Nvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Math13601392

Knowledge Not comparable

Llama 3.1 Nemotron Ultra 253b v1: —, Nvidia Llama 3.3 Nemotron Super 49b v1.5: 36.7 (#165)

BenchmarkLlama 3.1 Nemotron Ultra 253b v1Nvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Expert—1330

Multilingual Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads

Llama 3.1 Nemotron Ultra 253b v1: 43.1 (#187), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 45.5 (#168)

BenchmarkLlama 3.1 Nemotron Ultra 253b v1Nvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Non-English12821316
LMArena Russian12841332
LMArena Japanese—1300

Instruction Following Too close to call

Llama 3.1 Nemotron Ultra 253b v1: 69.0 (#178), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 68.6 (#188)

BenchmarkLlama 3.1 Nemotron Ultra 253b v1Nvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Instruction Following13081299

Long Context Too close to call

Llama 3.1 Nemotron Ultra 253b v1: 39.5 (#177), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 40.0 (#164)

BenchmarkLlama 3.1 Nemotron Ultra 253b v1Nvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Longer Query12991315

Writing & Preference Too close to call

Llama 3.1 Nemotron Ultra 253b v1: 52.2 (#175), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 53.1 (#159)

BenchmarkLlama 3.1 Nemotron Ultra 253b v1Nvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Text13201338
LMArena Creative Writing13141307
LMArena Multi-Turn13171334

Frequently asked questions

Is Llama 3.1 Nemotron Ultra 253b v1 better than Nvidia Llama 3.3 Nemotron Super 49b v1.5?

Nvidia Llama 3.3 Nemotron Super 49b v1.5 is the stronger model overall, scoring 40.3 to 36.7 on the Noometry Index.

Is Llama 3.1 Nemotron Ultra 253b v1 or Nvidia Llama 3.3 Nemotron Super 49b v1.5 better for coding?

Nvidia Llama 3.3 Nemotron Super 49b v1.5 scores higher on coding benchmarks: 39.8 versus 38.4 in the Noometry coding category.

How many benchmarks do Llama 3.1 Nemotron Ultra 253b v1 and Nvidia Llama 3.3 Nemotron Super 49b v1.5 share?

10 benchmarks have published results for both models. Llama 3.1 Nemotron Ultra 253b v1 has 11 scored results on Noometry and Nvidia Llama 3.3 Nemotron Super 49b v1.5 has 12.

Related comparisons

Go deeper