Noometry

Model comparison

Llama 4 Scout vs StarCoder 2 3B

Llama 4 Scout has enough public results to be ranked (#330); StarCoder 2 3B does not yet, so treat this comparison as directional.

Last verified . 2 shared benchmarks.

Llama 4 Scout Meta

27.7

Rank #330 Confirmed

StarCoder 2 3B NVIDIA

36.3

Unranked Sparse

Summary

  • They share 2 benchmarks with published results for both. Llama 4 Scout scores higher in 0 categories and StarCoder 2 3B in 1 category; one gap is clear of the uncertainty.
  • The widest gap is in coding, where StarCoder 2 3B leads 33.5 to 20.2.
  • The biggest single-benchmark swing is BigCodeBench Complete: 43.1% for Llama 4 Scout and 21.4% for StarCoder 2 3B.

Side by side

Llama 4 ScoutStarCoder 2 3B
ProviderMetaNVIDIA
Noometry Index27.736.3
Released2025-04-052024-02-22
WeightsOpenOpen
Context window128K—
Max output4K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.30—
Results tracked437

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

Category by category

Coding StarCoder 2 3B leads

Llama 4 Scout: 20.2 (#339), StarCoder 2 3B: 33.5

BenchmarkLlama 4 ScoutStarCoder 2 3B
BigCodeBench Complete43.1%21.4%
SWE-bench Verified (bash only)9.1%—
SciCode17%—
LMArena Coding1286—
HumanEval+—27.4%

Agentic & Tool Use Not comparable

Llama 4 Scout: 24.6 (#119), StarCoder 2 3B: —

BenchmarkLlama 4 ScoutStarCoder 2 3B
Berkeley Function Calling Leaderboard28.1%—

Reasoning Not comparable

Llama 4 Scout: 9.1 (#345), StarCoder 2 3B: —

BenchmarkLlama 4 ScoutStarCoder 2 3B
Epoch Capabilities Index129.6488.76
ARC-AGI-20%—
Kagi LLM Benchmark36.9%—
ARC-AGI-10.5%—
CritPt0%—
LMArena Hard Prompts1266—
DTBench57.9%—
LMCA12%—
ForecastBench57.5—
WinoGrande—57.1%

Math Not comparable

Llama 4 Scout: 19.6 (#286), StarCoder 2 3B: —

BenchmarkLlama 4 ScoutStarCoder 2 3B
OTIS Mock AIME 2024-20257.8%—
Omni-MATH37.3%—
LMArena Math1287—
MATH Level 562.3%—
FrontierMath (Feb 2025 set)0%—
GSM8K—21.6%

Knowledge Not comparable

Llama 4 Scout: 31.9 (#217), StarCoder 2 3B: —

BenchmarkLlama 4 ScoutStarCoder 2 3B
GPQA Diamond51.8%—
MMLU-Pro74.2%—
Vectara Hallucination Rate7.7%—
GPQA (HELM)50.7%—
LMArena Expert1235—
ARC (AI2) Challenge—34.2%
MMLU—36.6%

Multimodal Not comparable

Llama 4 Scout: 32.2 (#102), StarCoder 2 3B: —

BenchmarkLlama 4 ScoutStarCoder 2 3B
LMArena Vision1118—
SpatialViz-Bench34.2%—

Multilingual Not comparable

Llama 4 Scout: 41.0 (#212), StarCoder 2 3B: —

BenchmarkLlama 4 ScoutStarCoder 2 3B
LMArena Non-English1252—
LMArena Chinese1255—
LMArena French1282—
LMArena German1272—
LMArena Japanese1206—
LMArena Korean1207—
LMArena Russian1263—
LMArena Spanish1278—

Instruction Following Not comparable

Llama 4 Scout: 65.8 (#217), StarCoder 2 3B: —

BenchmarkLlama 4 ScoutStarCoder 2 3B
IFEval81.8%—
LMArena Instruction Following1248—

Long Context Not comparable

Llama 4 Scout: 27.5 (#294), StarCoder 2 3B: —

BenchmarkLlama 4 ScoutStarCoder 2 3B
Fiction.LiveBench36%—
LMArena Longer Query1265—

Writing & Preference Not comparable

Llama 4 Scout: 37.0 (#261), StarCoder 2 3B: —

BenchmarkLlama 4 ScoutStarCoder 2 3B
LMArena Text1279—
LMArena Creative Writing1249—
EQ-Bench Creative Writing783—
WildBench78%—
LMArena Multi-Turn1280—

Frequently asked questions

Is Llama 4 Scout better than StarCoder 2 3B?

Llama 4 Scout has enough public results to be ranked (#330); StarCoder 2 3B does not yet, so treat this comparison as directional.

Is Llama 4 Scout or StarCoder 2 3B better for coding?

StarCoder 2 3B scores higher on coding benchmarks: 33.5 versus 20.2 in the Noometry coding category.

How many benchmarks do Llama 4 Scout and StarCoder 2 3B share?

2 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and StarCoder 2 3B has 7.

Related comparisons

Go deeper