Noometry

Model comparison

Amazon Nova Micro vs Deepseek Coder v2

Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 30.4 on the Noometry Index.

Last verified . 17 shared benchmarks.

Amazon Nova Micro Amazon

30.4

Rank #294 Confirmed

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Amazon Nova Micro scores higher in 2 categories and Deepseek Coder v2 in 6 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Deepseek Coder v2 leads 34.9 to 26.9.
  • Deepseek Coder v2 has downloadable open weights; the other is API-only.

Side by side

Amazon Nova MicroDeepseek Coder v2
ProviderAmazonDeepSeek
Noometry Index30.435.9
Released2024-12-032024-06-17
WeightsProprietaryOpen
Context window128K—
Max output10K—
Input $ / M tokens$0.035—
Output $ / M tokens$0.14—
Results tracked3224

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

Category by category

Coding Deepseek Coder v2 leads

Amazon Nova Micro: 30.5 (#295), Deepseek Coder v2: 38.1 (#183)

BenchmarkAmazon Nova MicroDeepseek Coder v2
LMArena Coding12181251
BigCodeBench Instruct—48.2%
LiveBench Coding20.2%—
BigCodeBench Complete—59.7%
HumanEval+—82.3%
MBPP+—75.1%

Agentic & Tool Use Not comparable

Amazon Nova Micro: 22.1 (#132), Deepseek Coder v2: —

BenchmarkAmazon Nova MicroDeepseek Coder v2
Berkeley Function Calling Leaderboard22.3%—

Reasoning Deepseek Coder v2 leads

Amazon Nova Micro: 17.4 (#294), Deepseek Coder v2: 23.6 (#176)

BenchmarkAmazon Nova MicroDeepseek Coder v2
LMArena Hard Prompts11911207
LiveBench Reasoning25.1%—
LiveBench Data Analysis34%—
LiveBench29.6%—
WinoGrande—83.7%

Math Deepseek Coder v2 leads

Amazon Nova Micro: 26.9 (#254), Deepseek Coder v2: 34.9 (#190)

BenchmarkAmazon Nova MicroDeepseek Coder v2
LMArena Math12061241
Omni-MATH21.4%—
LiveBench Math34.5%—
GSM8K—94.5%

Knowledge Deepseek Coder v2 leads

Amazon Nova Micro: 29.6 (#237), Deepseek Coder v2: 32.3 (#212)

BenchmarkAmazon Nova MicroDeepseek Coder v2
LMArena Expert11841181
MMLU-Pro51.1%—
Vectara Hallucination Rate5.5%—
GPQA (HELM)38.3%—
ARC (AI2) Challenge—64.3%
MMLU70.8%—

Multilingual Too close to call

Amazon Nova Micro: 36.5 (#239), Deepseek Coder v2: 36.3 (#240)

BenchmarkAmazon Nova MicroDeepseek Coder v2
LMArena Non-English11861182
LMArena Chinese12091201
LMArena French12381185
LMArena German11921164
LMArena Japanese11541126
LMArena Korean11501104
LMArena Russian11851188
LMArena Spanish12251153

Instruction Following Deepseek Coder v2 leads

Amazon Nova Micro: 56.3 (#272), Deepseek Coder v2: 61.7 (#242)

BenchmarkAmazon Nova MicroDeepseek Coder v2
LMArena Instruction Following11741180
LiveBench Instruction Following48%—
IFEval76%—

Long Context Too close to call

Amazon Nova Micro: 36.5 (#229), Deepseek Coder v2: 37.0 (#224)

BenchmarkAmazon Nova MicroDeepseek Coder v2
LMArena Longer Query12051219

Writing & Preference Amazon Nova Micro leads

Amazon Nova Micro: 39.5 (#247), Deepseek Coder v2: 38.2 (#253)

BenchmarkAmazon Nova MicroDeepseek Coder v2
LMArena Text12081191
LMArena Creative Writing11721120
LMArena Multi-Turn11781177
WildBench74.3%—
LiveBench Language15.8%—

Frequently asked questions

Is Amazon Nova Micro better than Deepseek Coder v2?

Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 30.4 on the Noometry Index.

Is Amazon Nova Micro or Deepseek Coder v2 better for coding?

Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 30.5 in the Noometry coding category.

How many benchmarks do Amazon Nova Micro and Deepseek Coder v2 share?

17 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Deepseek Coder v2 has 24.

Related comparisons

Go deeper