Model comparison

Llama 13b vs Llama 3.1 Nemotron Ultra 253b v1

Llama 3.1 Nemotron Ultra 253b v1 is the stronger model overall, scoring 36.7 to 24.4 on the Noometry Index.

Last verified . 8 shared benchmarks.

Llama 13b Meta

24.4

Rank #348 Confirmed

Summary

  • They share 8 benchmarks with published results for both. Llama 13b scores higher in 0 categories and Llama 3.1 Nemotron Ultra 253b v1 in 6 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Llama 3.1 Nemotron Ultra 253b v1 leads 52.2 to 13.8.

Side by side

Llama 13b and Llama 3.1 Nemotron Ultra 253b v1 specifications
Llama 13bLlama 3.1 Nemotron Ultra 253b v1
ProviderMetaNVIDIA
Noometry Index24.436.7
Released2023-02-24—
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2111

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

Category by category

Coding Llama 3.1 Nemotron Ultra 253b v1 leads

Llama 13b: 21.4 (#337), Llama 3.1 Nemotron Ultra 253b v1: 38.4 (#177)

Coding benchmarks
BenchmarkLlama 13bLlama 3.1 Nemotron Ultra 253b v1
LMArena Coding6831312

Agentic & Tool Use Not comparable

Llama 13b: —, Llama 3.1 Nemotron Ultra 253b v1: 15.7 (#149)

Agentic & Tool Use benchmarks
BenchmarkLlama 13bLlama 3.1 Nemotron Ultra 253b v1
Berkeley Function Calling Leaderboard—10%

Reasoning Llama 3.1 Nemotron Ultra 253b v1 leads

Llama 13b: 14.0 (#329), Llama 3.1 Nemotron Ultra 253b v1: 26.3 (#134)

Reasoning benchmarks
BenchmarkLlama 13bLlama 3.1 Nemotron Ultra 253b v1
LMArena Hard Prompts7281316
BIG-Bench Hard37.9%—
Epoch Capabilities Index100.58—
HellaSwag79.2%—
LAMBADA75.2%—
PIQA80.1%—
WinoGrande73%—

Math Llama 3.1 Nemotron Ultra 253b v1 leads

Llama 13b: 26.7 (#256), Llama 3.1 Nemotron Ultra 253b v1: 37.5 (#152)

Math benchmarks
BenchmarkLlama 13bLlama 3.1 Nemotron Ultra 253b v1
LMArena Math8381360
GSM8K20.6%—

Knowledge Not comparable

Llama 13b: —, Llama 3.1 Nemotron Ultra 253b v1: —

Knowledge benchmarks
BenchmarkLlama 13bLlama 3.1 Nemotron Ultra 253b v1
ARC (AI2) Challenge52.7%—
BoolQ78.7%—
MMLU47.7%—
OpenBookQA56.4%—
TriviaQA77.9%—

Multimodal Not comparable

Llama 13b: —, Llama 3.1 Nemotron Ultra 253b v1: —

Multimodal benchmarks
BenchmarkLlama 13bLlama 3.1 Nemotron Ultra 253b v1
ScienceQA43.3%—

Multilingual Llama 3.1 Nemotron Ultra 253b v1 leads

Llama 13b: 16.6 (#297), Llama 3.1 Nemotron Ultra 253b v1: 43.1 (#187)

Multilingual benchmarks
BenchmarkLlama 13bLlama 3.1 Nemotron Ultra 253b v1
LMArena Non-English8191282
LMArena Russian—1284

Instruction Following Llama 3.1 Nemotron Ultra 253b v1 leads

Llama 13b: 36.7 (#305), Llama 3.1 Nemotron Ultra 253b v1: 69.0 (#178)

Instruction Following benchmarks
BenchmarkLlama 13bLlama 3.1 Nemotron Ultra 253b v1
LMArena Instruction Following7811308

Long Context Not comparable

Llama 13b: —, Llama 3.1 Nemotron Ultra 253b v1: 39.5 (#177)

Long Context benchmarks
BenchmarkLlama 13bLlama 3.1 Nemotron Ultra 253b v1
LMArena Longer Query—1299

Writing & Preference Llama 3.1 Nemotron Ultra 253b v1 leads

Llama 13b: 13.8 (#312), Llama 3.1 Nemotron Ultra 253b v1: 52.2 (#175)

Writing & Preference benchmarks
BenchmarkLlama 13bLlama 3.1 Nemotron Ultra 253b v1
LMArena Text8341320
LMArena Creative Writing7941314
LMArena Multi-Turn7531317

Frequently asked questions

Is Llama 13b 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 24.4 on the Noometry Index.

Is Llama 13b 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 21.4 in the Noometry coding category.

How many benchmarks do Llama 13b and Llama 3.1 Nemotron Ultra 253b v1 share?

8 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Llama 3.1 Nemotron Ultra 253b v1 has 11.

Related comparisons

Go deeper