Noometry

Model comparison

Deepseek Coder v2 vs Phi-3.5-mini

Deepseek Coder v2 has enough public results to be ranked (#220); Phi-3.5-mini does not yet, so treat this comparison as directional.

Last verified . 3 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

Phi-3.5-mini Microsoft

36.9

Unranked Sparse

Summary

  • They share 3 benchmarks with published results for both. Deepseek Coder v2 scores higher in 1 category and Phi-3.5-mini in 0 categories; one gap is clear of the uncertainty.
  • The widest gap is in coding, where Deepseek Coder v2 leads 38.1 to 34.6.
  • The biggest single-benchmark swing is BigCodeBench Complete: 59.7% for Deepseek Coder v2 and 38.5% for Phi-3.5-mini.

Side by side

Deepseek Coder v2Phi-3.5-mini
ProviderDeepSeekMicrosoft
Noometry Index35.936.9
Released2024-06-172024-08-16
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked245

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-3.5-mini: 34.6 (#232)

BenchmarkDeepseek Coder v2Phi-3.5-mini
BigCodeBench Instruct48.2%32.8%
BigCodeBench Complete59.7%38.5%
LMArena Coding1251—
HumanEval+82.3%—
MBPP+75.1%—

Reasoning Not comparable

Deepseek Coder v2: 23.6 (#176), Phi-3.5-mini: —

BenchmarkDeepseek Coder v2Phi-3.5-mini
LMArena Hard Prompts1207—
PIQA—81%
WinoGrande83.7%—

Math Not comparable

Deepseek Coder v2: 34.9 (#190), Phi-3.5-mini: —

BenchmarkDeepseek Coder v2Phi-3.5-mini
GSM8K94.5%86.2%
LMArena Math1241—

Knowledge Not comparable

Deepseek Coder v2: 32.3 (#212), Phi-3.5-mini: —

BenchmarkDeepseek Coder v2Phi-3.5-mini
LMArena Expert1181—
ARC (AI2) Challenge64.3%—
BoolQ—78%

Multilingual Not comparable

Deepseek Coder v2: 36.3 (#240), Phi-3.5-mini: —

BenchmarkDeepseek Coder v2Phi-3.5-mini
LMArena Non-English1182—
LMArena Chinese1201—
LMArena French1185—
LMArena German1164—
LMArena Japanese1126—
LMArena Korean1104—
LMArena Russian1188—
LMArena Spanish1153—

Instruction Following Not comparable

Deepseek Coder v2: 61.7 (#242), Phi-3.5-mini: —

BenchmarkDeepseek Coder v2Phi-3.5-mini
LMArena Instruction Following1180—

Long Context Not comparable

Deepseek Coder v2: 37.0 (#224), Phi-3.5-mini: —

BenchmarkDeepseek Coder v2Phi-3.5-mini
LMArena Longer Query1219—

Writing & Preference Not comparable

Deepseek Coder v2: 38.2 (#253), Phi-3.5-mini: —

BenchmarkDeepseek Coder v2Phi-3.5-mini
LMArena Text1191—
LMArena Creative Writing1120—
LMArena Multi-Turn1177—

Frequently asked questions

Is Deepseek Coder v2 better than Phi-3.5-mini?

Deepseek Coder v2 has enough public results to be ranked (#220); Phi-3.5-mini does not yet, so treat this comparison as directional.

Is Deepseek Coder v2 or Phi-3.5-mini better for coding?

Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 34.6 in the Noometry coding category.

How many benchmarks do Deepseek Coder v2 and Phi-3.5-mini share?

3 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Phi-3.5-mini has 5.

Related comparisons

Go deeper