Noometry

Model comparison

DeepSeek Coder 33B vs DeepSeek LLM 67B

DeepSeek LLM 67B has enough public results to be ranked (#347); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

DeepSeek Coder 33B DeepSeek

38.9

Unranked Sparse

DeepSeek LLM 67B DeepSeek

24.9

Rank #347 Confirmed

Summary

  • They share 1 benchmark with published results for both. DeepSeek Coder 33B scores higher in 1 category and DeepSeek LLM 67B in 0 categories; one gap is clear of the uncertainty.
  • The widest gap is in coding, where DeepSeek Coder 33B leads 38.0 to 31.9.

Side by side

DeepSeek Coder 33BDeepSeek LLM 67B
ProviderDeepSeekDeepSeek
Noometry Index38.924.9
Released2023-11-022023-11-29
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked915

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

Category by category

Coding DeepSeek Coder 33B leads

DeepSeek Coder 33B: 38.0 (#184), DeepSeek LLM 67B: 31.9 (#278)

BenchmarkDeepSeek Coder 33BDeepSeek LLM 67B
BigCodeBench Instruct42%—
LMArena Coding—1096
BigCodeBench Complete51.1%—
HumanEval+75%—
MBPP+70.1%—

Reasoning Not comparable

DeepSeek Coder 33B: —, DeepSeek LLM 67B: 16.5 (#304)

BenchmarkDeepSeek Coder 33BDeepSeek LLM 67B
Epoch Capabilities Index96.32110.5
Chess Puzzles—0%
LMArena Hard Prompts—1070
WinoGrande62%—

Math Not comparable

DeepSeek Coder 33B: —, DeepSeek LLM 67B: 8.7 (#324)

BenchmarkDeepSeek Coder 33BDeepSeek LLM 67B
OTIS Mock AIME 2024-2025—0.8%
LMArena Math—1108
MATH Level 5—6.4%
GSM8K35.4%—

Knowledge Not comparable

DeepSeek Coder 33B: —, DeepSeek LLM 67B: 7.0 (#313)

BenchmarkDeepSeek Coder 33BDeepSeek LLM 67B
GPQA Diamond—24.6%
ARC (AI2) Challenge42.2%—
MMLU39.4%—

Multilingual Not comparable

DeepSeek Coder 33B: —, DeepSeek LLM 67B: 29.4 (#267)

BenchmarkDeepSeek Coder 33BDeepSeek LLM 67B
LMArena Non-English—1073
LMArena Chinese—1132

Instruction Following Not comparable

DeepSeek Coder 33B: —, DeepSeek LLM 67B: 55.4 (#277)

BenchmarkDeepSeek Coder 33BDeepSeek LLM 67B
LMArena Instruction Following—1079

Long Context Not comparable

DeepSeek Coder 33B: —, DeepSeek LLM 67B: 33.1 (#265)

BenchmarkDeepSeek Coder 33BDeepSeek LLM 67B
LMArena Longer Query—1092

Writing & Preference Not comparable

DeepSeek Coder 33B: —, DeepSeek LLM 67B: 31.6 (#282)

BenchmarkDeepSeek Coder 33BDeepSeek LLM 67B
LMArena Text—1105
LMArena Creative Writing—1067
LMArena Multi-Turn—1082

Frequently asked questions

Is DeepSeek Coder 33B better than DeepSeek LLM 67B?

DeepSeek LLM 67B has enough public results to be ranked (#347); DeepSeek Coder 33B does not yet, so treat this comparison as directional.

Is DeepSeek Coder 33B or DeepSeek LLM 67B better for coding?

DeepSeek Coder 33B scores higher on coding benchmarks: 38.0 versus 31.9 in the Noometry coding category.

How many benchmarks do DeepSeek Coder 33B and DeepSeek LLM 67B share?

1 benchmark has published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and DeepSeek LLM 67B has 15.

Related comparisons

Go deeper