Model comparison

Llama 3.1 Nemotron 51b Instruct vs StarCoder 2 15B

Llama 3.1 Nemotron 51b Instruct has enough public results to be ranked (#219); StarCoder 2 15B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

StarCoder 2 15B NVIDIA

37.5

Unranked Sparse

Side by side

Llama 3.1 Nemotron 51b Instruct and StarCoder 2 15B specifications
Llama 3.1 Nemotron 51b InstructStarCoder 2 15B
ProviderNVIDIANVIDIA
Noometry Index35.237.5
Released—2024-02-20
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked127

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

Category by category

Coding Too close to call

Llama 3.1 Nemotron 51b Instruct: 35.0 (#219), StarCoder 2 15B: 36.0

Coding benchmarks
BenchmarkLlama 3.1 Nemotron 51b InstructStarCoder 2 15B
LMArena Coding1223—
BigCodeBench Complete—38.4%
HumanEval+—37.8%

Reasoning Not comparable

Llama 3.1 Nemotron 51b Instruct: 22.5 (#177), StarCoder 2 15B: —

Reasoning benchmarks
BenchmarkLlama 3.1 Nemotron 51b InstructStarCoder 2 15B
LMArena Hard Prompts1204—
Epoch Capabilities Index—104.61
WinoGrande—64.3%

Math Not comparable

Llama 3.1 Nemotron 51b Instruct: 32.0 (#189), StarCoder 2 15B: —

Math benchmarks
BenchmarkLlama 3.1 Nemotron 51b InstructStarCoder 2 15B
LMArena Math1230—
GSM8K—57.7%

Knowledge Not comparable

Llama 3.1 Nemotron 51b Instruct: 31.3 (#213), StarCoder 2 15B: —

Knowledge benchmarks
BenchmarkLlama 3.1 Nemotron 51b InstructStarCoder 2 15B
LMArena Expert1167—
ARC (AI2) Challenge—47.2%
MMLU—64.1%

Multilingual Not comparable

Llama 3.1 Nemotron 51b Instruct: 36.3 (#236), StarCoder 2 15B: —

Multilingual benchmarks
BenchmarkLlama 3.1 Nemotron 51b InstructStarCoder 2 15B
LMArena Non-English1181—
LMArena Chinese1179—
LMArena Russian1186—

Instruction Following Not comparable

Llama 3.1 Nemotron 51b Instruct: 63.2 (#228), StarCoder 2 15B: —

Instruction Following benchmarks
BenchmarkLlama 3.1 Nemotron 51b InstructStarCoder 2 15B
LMArena Instruction Following1201—

Long Context Not comparable

Llama 3.1 Nemotron 51b Instruct: 36.5 (#225), StarCoder 2 15B: —

Long Context benchmarks
BenchmarkLlama 3.1 Nemotron 51b InstructStarCoder 2 15B
LMArena Longer Query1205—

Writing & Preference Not comparable

Llama 3.1 Nemotron 51b Instruct: 43.5 (#224), StarCoder 2 15B: —

Writing & Preference benchmarks
BenchmarkLlama 3.1 Nemotron 51b InstructStarCoder 2 15B
LMArena Text1228—
LMArena Creative Writing1213—
LMArena Multi-Turn1227—

Frequently asked questions

Is Llama 3.1 Nemotron 51b Instruct better than StarCoder 2 15B?

Llama 3.1 Nemotron 51b Instruct has enough public results to be ranked (#219); StarCoder 2 15B does not yet, so treat this comparison as directional.

Is Llama 3.1 Nemotron 51b Instruct or StarCoder 2 15B better for coding?

They score almost the same on coding (35.0 vs 36.0); test both on your own repository before choosing.

How many benchmarks do Llama 3.1 Nemotron 51b Instruct and StarCoder 2 15B share?

0 benchmarks have published results for both models. Llama 3.1 Nemotron 51b Instruct has 12 scored results on Noometry and StarCoder 2 15B has 7.

Related comparisons

Go deeper