Noometry

Model comparison

DeepSeek LLM 67B vs StarCoder 2 3B

DeepSeek LLM 67B has enough public results to be ranked (#347); StarCoder 2 3B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

StarCoder 2 3B NVIDIA

36.3

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. DeepSeek LLM 67B scores higher in 0 categories and StarCoder 2 3B in 1 category; one gap is clear of the uncertainty.

Side by side

DeepSeek LLM 67BStarCoder 2 3B
ProviderDeepSeekNVIDIA
Noometry Index24.936.3
Released2023-11-292024-02-22
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked157

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

Category by category

Coding StarCoder 2 3B leads

DeepSeek LLM 67B: 31.9 (#278), StarCoder 2 3B: 33.5

BenchmarkDeepSeek LLM 67BStarCoder 2 3B
LMArena Coding1096—
BigCodeBench Complete—21.4%
HumanEval+—27.4%

Reasoning Not comparable

DeepSeek LLM 67B: 16.5 (#304), StarCoder 2 3B: —

BenchmarkDeepSeek LLM 67BStarCoder 2 3B
Epoch Capabilities Index110.588.76
Chess Puzzles0%—
LMArena Hard Prompts1070—
WinoGrande—57.1%

Math Not comparable

DeepSeek LLM 67B: 8.7 (#324), StarCoder 2 3B: —

BenchmarkDeepSeek LLM 67BStarCoder 2 3B
OTIS Mock AIME 2024-20250.8%—
LMArena Math1108—
MATH Level 56.4%—
GSM8K—21.6%

Knowledge Not comparable

DeepSeek LLM 67B: 7.0 (#313), StarCoder 2 3B: —

BenchmarkDeepSeek LLM 67BStarCoder 2 3B
GPQA Diamond24.6%—
ARC (AI2) Challenge—34.2%
MMLU—36.6%

Multilingual Not comparable

DeepSeek LLM 67B: 29.4 (#267), StarCoder 2 3B: —

BenchmarkDeepSeek LLM 67BStarCoder 2 3B
LMArena Non-English1073—
LMArena Chinese1132—

Instruction Following Not comparable

DeepSeek LLM 67B: 55.4 (#277), StarCoder 2 3B: —

BenchmarkDeepSeek LLM 67BStarCoder 2 3B
LMArena Instruction Following1079—

Long Context Not comparable

DeepSeek LLM 67B: 33.1 (#265), StarCoder 2 3B: —

BenchmarkDeepSeek LLM 67BStarCoder 2 3B
LMArena Longer Query1092—

Writing & Preference Not comparable

DeepSeek LLM 67B: 31.6 (#282), StarCoder 2 3B: —

BenchmarkDeepSeek LLM 67BStarCoder 2 3B
LMArena Text1105—
LMArena Creative Writing1067—
LMArena Multi-Turn1082—

Frequently asked questions

Is DeepSeek LLM 67B better than StarCoder 2 3B?

DeepSeek LLM 67B has enough public results to be ranked (#347); StarCoder 2 3B does not yet, so treat this comparison as directional.

Is DeepSeek LLM 67B or StarCoder 2 3B better for coding?

StarCoder 2 3B scores higher on coding benchmarks: 33.5 versus 31.9 in the Noometry coding category.

How many benchmarks do DeepSeek LLM 67B and StarCoder 2 3B share?

1 benchmark has published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and StarCoder 2 3B has 7.

Related comparisons

Go deeper