Noometry

Model comparison

Deepseek Coder v2 vs Phi 3 Small 8k Instruct

Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 29.3 on the Noometry Index.

Last verified . 19 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

Phi 3 Small 8k Instruct Microsoft

29.3

Rank #314 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Deepseek Coder v2 scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Deepseek Coder v2 leads 38.1 to 27.9.

Side by side

Deepseek Coder v2Phi 3 Small 8k Instruct
ProviderDeepSeekMicrosoft
Noometry Index35.929.3
Released2024-06-172024-04-23
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2432

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

Category by category

Coding Deepseek Coder v2 leads

Deepseek Coder v2: 38.1 (#183), Phi 3 Small 8k Instruct: 27.9 (#318)

BenchmarkDeepseek Coder v2Phi 3 Small 8k Instruct
LMArena Coding12511101
BigCodeBench Instruct48.2%—
LiveBench Coding—20.3%
BigCodeBench Complete59.7%—
HumanEval+82.3%—
MBPP+75.1%—

Reasoning Deepseek Coder v2 leads

Deepseek Coder v2: 23.6 (#176), Phi 3 Small 8k Instruct: 14.8 (#323)

BenchmarkDeepseek Coder v2Phi 3 Small 8k Instruct
LMArena Hard Prompts12071100
WinoGrande83.7%81.5%
LiveBench Reasoning—15.9%
LiveBench Data Analysis—30.3%
Adversarial NLI—58.1%
BIG-Bench Hard—79.1%
HellaSwag—77%
LiveBench—24%

Math Deepseek Coder v2 leads

Deepseek Coder v2: 34.9 (#190), Phi 3 Small 8k Instruct: 27.6 (#248)

BenchmarkDeepseek Coder v2Phi 3 Small 8k Instruct
LMArena Math12411151
LiveBench Math—17.6%
GSM8K94.5%—

Knowledge Deepseek Coder v2 leads

Deepseek Coder v2: 32.3 (#212), Phi 3 Small 8k Instruct: 29.1 (#240)

BenchmarkDeepseek Coder v2Phi 3 Small 8k Instruct
LMArena Expert11811067
ARC (AI2) Challenge64.3%90.7%
MMLU—75.7%
OpenBookQA—88%
TriviaQA—58.1%

Multilingual Deepseek Coder v2 leads

Deepseek Coder v2: 36.3 (#240), Phi 3 Small 8k Instruct: 28.5 (#272)

BenchmarkDeepseek Coder v2Phi 3 Small 8k Instruct
LMArena Non-English11821058
LMArena Chinese12011061
LMArena French11851135
LMArena German11641080
LMArena Japanese1126966
LMArena Korean1104894
LMArena Russian11881111
LMArena Spanish11531111

Instruction Following Deepseek Coder v2 leads

Deepseek Coder v2: 61.7 (#242), Phi 3 Small 8k Instruct: 51.9 (#292)

BenchmarkDeepseek Coder v2Phi 3 Small 8k Instruct
LMArena Instruction Following11801087
LiveBench Instruction Following—47.2%

Long Context Deepseek Coder v2 leads

Deepseek Coder v2: 37.0 (#224), Phi 3 Small 8k Instruct: 33.0 (#267)

BenchmarkDeepseek Coder v2Phi 3 Small 8k Instruct
LMArena Longer Query12191088

Writing & Preference Deepseek Coder v2 leads

Deepseek Coder v2: 38.2 (#253), Phi 3 Small 8k Instruct: 31.1 (#284)

BenchmarkDeepseek Coder v2Phi 3 Small 8k Instruct
LMArena Text11911110
LMArena Creative Writing11201083
LMArena Multi-Turn11771068
LiveBench Language—12.9%

Frequently asked questions

Is Deepseek Coder v2 better than Phi 3 Small 8k Instruct?

Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 29.3 on the Noometry Index.

Is Deepseek Coder v2 or Phi 3 Small 8k Instruct better for coding?

Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 27.9 in the Noometry coding category.

How many benchmarks do Deepseek Coder v2 and Phi 3 Small 8k Instruct share?

19 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Phi 3 Small 8k Instruct has 32.

Related comparisons

Go deeper