Model comparison

DeepSeek-V2 (MoE-236B, May 2024) vs Phi 3 Mini 4k Instruct June 2024

Phi 3 Mini 4k Instruct June 2024 has enough public results to be ranked (#276); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Summary

  • The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 31.8.

Side by side

DeepSeek-V2 (MoE-236B, May 2024) and Phi 3 Mini 4k Instruct June 2024 specifications
DeepSeek-V2 (MoE-236B, May 2024)Phi 3 Mini 4k Instruct June 2024
ProviderDeepSeekMicrosoft
Noometry Index40.331.3
Released2024-05-07—
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked1015

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

Category by category

Coding DeepSeek-V2 (MoE-236B, May 2024) leads

DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), Phi 3 Mini 4k Instruct June 2024: 31.8 (#279)

Coding benchmarks
BenchmarkDeepSeek-V2 (MoE-236B, May 2024)Phi 3 Mini 4k Instruct June 2024
BigCodeBench Instruct48.9%—
LMArena Coding—1093
BigCodeBench Complete59.4%—

Reasoning Not comparable

DeepSeek-V2 (MoE-236B, May 2024): —, Phi 3 Mini 4k Instruct June 2024: 20.8 (#231)

Reasoning benchmarks
BenchmarkDeepSeek-V2 (MoE-236B, May 2024)Phi 3 Mini 4k Instruct June 2024
LMArena Hard Prompts—1087
BIG-Bench Hard78.8%—
Epoch Capabilities Index124.77—
HellaSwag87.1%—
PIQA83.9%—
WinoGrande86.3%—

Math Not comparable

DeepSeek-V2 (MoE-236B, May 2024): —, Phi 3 Mini 4k Instruct June 2024: 33.0 (#208)

Math benchmarks
BenchmarkDeepSeek-V2 (MoE-236B, May 2024)Phi 3 Mini 4k Instruct June 2024
LMArena Math—1152

Knowledge Not comparable

DeepSeek-V2 (MoE-236B, May 2024): —, Phi 3 Mini 4k Instruct June 2024: 28.6 (#244)

Knowledge benchmarks
BenchmarkDeepSeek-V2 (MoE-236B, May 2024)Phi 3 Mini 4k Instruct June 2024
LMArena Expert—1051
ARC (AI2) Challenge92.2%—
MMLU78.4%—
TriviaQA80%—

Multilingual Not comparable

DeepSeek-V2 (MoE-236B, May 2024): —, Phi 3 Mini 4k Instruct June 2024: 25.9 (#282)

Multilingual benchmarks
BenchmarkDeepSeek-V2 (MoE-236B, May 2024)Phi 3 Mini 4k Instruct June 2024
LMArena Non-English—1013
LMArena Chinese—1033
LMArena German—1031
LMArena Japanese—954
LMArena Korean—880
LMArena Russian—1019

Instruction Following Not comparable

DeepSeek-V2 (MoE-236B, May 2024): —, Phi 3 Mini 4k Instruct June 2024: 54.1 (#282)

Instruction Following benchmarks
BenchmarkDeepSeek-V2 (MoE-236B, May 2024)Phi 3 Mini 4k Instruct June 2024
LMArena Instruction Following—1058

Long Context Not comparable

DeepSeek-V2 (MoE-236B, May 2024): —, Phi 3 Mini 4k Instruct June 2024: 31.7 (#277)

Long Context benchmarks
BenchmarkDeepSeek-V2 (MoE-236B, May 2024)Phi 3 Mini 4k Instruct June 2024
LMArena Longer Query—1042

Writing & Preference Not comparable

DeepSeek-V2 (MoE-236B, May 2024): —, Phi 3 Mini 4k Instruct June 2024: 29.6 (#294)

Writing & Preference benchmarks
BenchmarkDeepSeek-V2 (MoE-236B, May 2024)Phi 3 Mini 4k Instruct June 2024
LMArena Text—1080
LMArena Creative Writing—1045
LMArena Multi-Turn—1049

Frequently asked questions

Is DeepSeek-V2 (MoE-236B, May 2024) better than Phi 3 Mini 4k Instruct June 2024?

Phi 3 Mini 4k Instruct June 2024 has enough public results to be ranked (#276); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

Is DeepSeek-V2 (MoE-236B, May 2024) or Phi 3 Mini 4k Instruct June 2024 better for coding?

DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 31.8 in the Noometry coding category.

How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Phi 3 Mini 4k Instruct June 2024 share?

0 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Phi 3 Mini 4k Instruct June 2024 has 15.

Related comparisons

Go deeper