Model comparison

Llama 4 Scout vs Nemotron-4 15B

Llama 4 Scout has enough public results to be ranked (#323); Nemotron-4 15B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Llama 4 Scout Meta

27.4

Rank #323 Confirmed

Nemotron-4 15B NVIDIA

—

Unranked

Summary

  • They share 1 benchmark with published results for both.
  • Llama 4 Scout has downloadable open weights; the other is API-only.

Side by side

Llama 4 Scout and Nemotron-4 15B specifications
Llama 4 ScoutNemotron-4 15B
ProviderMetaNVIDIA
Noometry Index27.4—
Released2025-04-052024-02-26
WeightsOpenProprietary
Context window128K—
Max output4K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.30—
Results tracked438

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

Category by category

Coding Not comparable

Llama 4 Scout: 19.9 (#334), Nemotron-4 15B: —

Coding benchmarks
BenchmarkLlama 4 ScoutNemotron-4 15B
SWE-bench Verified (bash only)9.1%—
SciCode17%—
LMArena Coding1286—
BigCodeBench Complete43.1%—

Agentic & Tool Use Not comparable

Llama 4 Scout: 24.4 (#109), Nemotron-4 15B: —

Agentic & Tool Use benchmarks
BenchmarkLlama 4 ScoutNemotron-4 15B
Berkeley Function Calling Leaderboard28.1%—

Reasoning Not comparable

Llama 4 Scout: 9.2 (#339), Nemotron-4 15B: —

Reasoning benchmarks
BenchmarkLlama 4 ScoutNemotron-4 15B
Epoch Capabilities Index129.64107.38
ARC-AGI-20%—
Kagi LLM Benchmark36.9%—
ARC-AGI-10.5%—
CritPt0%—
LMArena Hard Prompts1266—
DTBench57.9%—
LMCA12%—
BIG-Bench Hard—58.7%
ForecastBench57.5—
HellaSwag—82.4%
PIQA—82.4%
WinoGrande—78%

Math Not comparable

Llama 4 Scout: 18.4 (#280), Nemotron-4 15B: —

Math benchmarks
BenchmarkLlama 4 ScoutNemotron-4 15B
OTIS Mock AIME 2024-20257.8%—
Omni-MATH37.3%—
LMArena Math1286—
MATH Level 562.3%—
FrontierMath (Feb 2025 set)0%—
GSM8K—46%

Knowledge Not comparable

Llama 4 Scout: 31.8 (#208), Nemotron-4 15B: —

Knowledge benchmarks
BenchmarkLlama 4 ScoutNemotron-4 15B
GPQA Diamond51.8%—
MMLU-Pro74.2%—
Vectara Hallucination Rate7.7%—
GPQA (HELM)50.7%—
LMArena Expert1236—
ARC (AI2) Challenge—55.5%
MMLU—58.7%

Multimodal Not comparable

Llama 4 Scout: 31.6 (#98), Nemotron-4 15B: —

Multimodal benchmarks
BenchmarkLlama 4 ScoutNemotron-4 15B
LMArena Vision1118—
SpatialViz-Bench34.2%—

Multilingual Not comparable

Llama 4 Scout: 41.3 (#207), Nemotron-4 15B: —

Multilingual benchmarks
BenchmarkLlama 4 ScoutNemotron-4 15B
LMArena Non-English1253—
LMArena Chinese1256—
LMArena French1283—
LMArena German1274—
LMArena Japanese1209—
LMArena Korean1207—
LMArena Russian1263—
LMArena Spanish1277—

Instruction Following Not comparable

Llama 4 Scout: 66.0 (#212), Nemotron-4 15B: —

Instruction Following benchmarks
BenchmarkLlama 4 ScoutNemotron-4 15B
IFEval81.8%—
LMArena Instruction Following1248—

Long Context Not comparable

Llama 4 Scout: 27.5 (#289), Nemotron-4 15B: —

Long Context benchmarks
BenchmarkLlama 4 ScoutNemotron-4 15B
Fiction.LiveBench36%—
LMArena Longer Query1265—

Writing & Preference Not comparable

Llama 4 Scout: 37.1 (#256), Nemotron-4 15B: —

Writing & Preference benchmarks
BenchmarkLlama 4 ScoutNemotron-4 15B
LMArena Text1279—
LMArena Creative Writing1249—
EQ-Bench Creative Writing783—
WildBench78%—
LMArena Multi-Turn1281—

Frequently asked questions

Is Llama 4 Scout better than Nemotron-4 15B?

Llama 4 Scout has enough public results to be ranked (#323); Nemotron-4 15B does not yet, so treat this comparison as directional.

How many benchmarks do Llama 4 Scout and Nemotron-4 15B share?

1 benchmark has published results for both models. Llama 4 Scout has 43 scored results on Noometry and Nemotron-4 15B has 8.

Related comparisons

Go deeper