Noometry

Model comparison

Deepseek Coder v2 vs DeepSeek-V3

DeepSeek-V3 is the stronger model overall, scoring 39.5 to 35.9 on the Noometry Index.

Last verified . 23 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

DeepSeek-V3 DeepSeek

39.5

Rank #166 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Deepseek Coder v2 scores higher in 3 categories and DeepSeek-V3 in 5 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where DeepSeek-V3 leads 57.4 to 38.2.

Side by side

Deepseek Coder v2DeepSeek-V3
ProviderDeepSeekDeepSeek
Noometry Index35.939.5
Released2024-06-172024-12-26
WeightsOpenOpen
Context window—164K
Max output—164K
Input $ / M tokens—$0.24
Output $ / M tokens—$0.90
Results tracked2460

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

Category by category

Coding DeepSeek-V3 leads

Deepseek Coder v2: 38.1 (#183), DeepSeek-V3: 42.3 (#106)

BenchmarkDeepseek Coder v2DeepSeek-V3
BigCodeBench Instruct48.2%50%
LMArena Coding12511368
BigCodeBench Complete59.7%62.2%
HumanEval+82.3%86.6%
MBPP+75.1%73%
Aider Polyglot—55.1%
SciCode—35.8%
WeirdML—36.1%
LiveBench Coding—70.9%

Agentic & Tool Use Not comparable

Deepseek Coder v2: —, DeepSeek-V3: —

BenchmarkDeepseek Coder v2DeepSeek-V3
METR Time Horizons—49.6%

Reasoning Deepseek Coder v2 leads

Deepseek Coder v2: 23.6 (#176), DeepSeek-V3: 20.5 (#236)

BenchmarkDeepseek Coder v2DeepSeek-V3
LMArena Hard Prompts12071365
WinoGrande83.7%85.2%
SimpleBench—27.2%
Kagi LLM Benchmark—52.3%
CritPt—0%
LiveBench Reasoning—65.8%
DTBench—64.8%
LiveBench Data Analysis—60.9%
LMCA—15.5%
BIG-Bench Hard—87.5%
Epoch Capabilities Index—135.94
ForecastBench—59.1
HellaSwag—88.9%
LiveBench—66.9%
PIQA—84.7%

Math Deepseek Coder v2 leads

Deepseek Coder v2: 34.9 (#190), DeepSeek-V3: 32.1 (#219)

BenchmarkDeepseek Coder v2DeepSeek-V3
LMArena Math12411373
OTIS Mock AIME 2024-2025—37.8%
Omni-MATH—40.3%
LiveBench Math—73.5%
MATH Level 5—75.5%
FrontierMath (Feb 2025 set)—1.7%
GSM8K94.5%—

Knowledge DeepSeek-V3 leads

Deepseek Coder v2: 32.3 (#212), DeepSeek-V3: 37.5 (#155)

BenchmarkDeepseek Coder v2DeepSeek-V3
LMArena Expert11811351
ARC (AI2) Challenge64.3%95.3%
GPQA Diamond—67.6%
MMLU-Pro—72.3%
Confabulations—26.1%
Vectara Hallucination Rate—6.1%
GPQA (HELM)—53.8%
MMLU—87.2%
TriviaQA—82.9%

Multilingual DeepSeek-V3 leads

Deepseek Coder v2: 36.3 (#240), DeepSeek-V3: 48.5 (#143)

BenchmarkDeepseek Coder v2DeepSeek-V3
LMArena Non-English11821358
LMArena Chinese12011391
LMArena French11851385
LMArena German11641374
LMArena Japanese11261333
LMArena Korean11041319
LMArena Russian11881373
LMArena Spanish11531358

Instruction Following DeepSeek-V3 leads

Deepseek Coder v2: 61.7 (#242), DeepSeek-V3: 72.8 (#130)

BenchmarkDeepseek Coder v2DeepSeek-V3
LMArena Instruction Following11801345
LiveBench Instruction Following—81.5%
IFEval—83.2%

Long Context Deepseek Coder v2 leads

Deepseek Coder v2: 37.0 (#224), DeepSeek-V3: 34.0 (#253)

BenchmarkDeepseek Coder v2DeepSeek-V3
LMArena Longer Query12191352
Fiction.LiveBench—50%

Writing & Preference DeepSeek-V3 leads

Deepseek Coder v2: 38.2 (#253), DeepSeek-V3: 57.4 (#130)

BenchmarkDeepseek Coder v2DeepSeek-V3
LMArena Text11911375
LMArena Creative Writing11201364
LMArena Multi-Turn11771389
Short-Story Creative Writing—77%
EQ-Bench Creative Writing—1472
WildBench—83%
LiveBench Language—49.1%

Frequently asked questions

Is Deepseek Coder v2 better than DeepSeek-V3?

DeepSeek-V3 is the stronger model overall, scoring 39.5 to 35.9 on the Noometry Index.

Is Deepseek Coder v2 or DeepSeek-V3 better for coding?

DeepSeek-V3 scores higher on coding benchmarks: 42.3 versus 38.1 in the Noometry coding category.

How many benchmarks do Deepseek Coder v2 and DeepSeek-V3 share?

23 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and DeepSeek-V3 has 60.

Related comparisons

Go deeper