Noometry

Model comparison

Nemotron 4 340b Instruct 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 35.9 on the Noometry Index.

Last verified . 12 shared benchmarks.

Nemotron 4 340b Instruct NVIDIA

35.9

Rank #223 Confirmed

Nvidia Llama 3.3 Nemotron Super 49b v1.5 NVIDIA

40.3

Rank #151 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Nemotron 4 340b Instruct scores higher in 0 categories and Nvidia Llama 3.3 Nemotron Super 49b v1.5 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads 53.1 to 42.7.

Side by side

Nemotron 4 340b InstructNvidia Llama 3.3 Nemotron Super 49b v1.5
ProviderNVIDIANVIDIA
Noometry Index35.940.3
Released2024-06-142025-07-25
WeightsOpenOpen
Context window—131K
Max output—131K
Input $ / M tokens—$0.40
Output $ / M tokens—$0.40
Results tracked1712

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

Nemotron 4 340b Instruct: 35.2 (#228), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 39.8 (#154)

BenchmarkNemotron 4 340b InstructNvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Coding12091355

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

Nemotron 4 340b Instruct: 23.4 (#178), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 26.8 (#128)

BenchmarkNemotron 4 340b InstructNvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Hard Prompts12021336

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

Nemotron 4 340b Instruct: 34.3 (#195), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 38.2 (#141)

BenchmarkNemotron 4 340b InstructNvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Math12161392

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

Nemotron 4 340b Instruct: 32.0 (#216), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 36.7 (#165)

BenchmarkNemotron 4 340b InstructNvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Expert11711330

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

Nemotron 4 340b Instruct: 37.9 (#233), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 45.5 (#168)

BenchmarkNemotron 4 340b InstructNvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Non-English12061316
LMArena Japanese11281300
LMArena Russian12191332
LMArena Chinese1214—
LMArena French1197—
LMArena German1192—
LMArena Korean1148—
LMArena Spanish1195—

Instruction Following Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads

Nemotron 4 340b Instruct: 63.1 (#232), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 68.6 (#188)

BenchmarkNemotron 4 340b InstructNvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Instruction Following12031299

Long Context Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads

Nemotron 4 340b Instruct: 37.1 (#221), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 40.0 (#164)

BenchmarkNemotron 4 340b InstructNvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Longer Query12251315

Writing & Preference Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads

Nemotron 4 340b Instruct: 42.7 (#233), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 53.1 (#159)

BenchmarkNemotron 4 340b InstructNvidia Llama 3.3 Nemotron Super 49b v1.5
LMArena Text12251338
LMArena Creative Writing12031307
LMArena Multi-Turn12141334

Frequently asked questions

Is Nemotron 4 340b Instruct 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 35.9 on the Noometry Index.

Is Nemotron 4 340b Instruct 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 35.2 in the Noometry coding category.

How many benchmarks do Nemotron 4 340b Instruct and Nvidia Llama 3.3 Nemotron Super 49b v1.5 share?

12 benchmarks have published results for both models. Nemotron 4 340b Instruct has 17 scored results on Noometry and Nvidia Llama 3.3 Nemotron Super 49b v1.5 has 12.

Related comparisons

Go deeper