Noometry

Model comparison

DeepSeek LLM 67B vs Phi-3.5-MoE

DeepSeek LLM 67B has enough public results to be ranked (#341); Phi-3.5-MoE does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

DeepSeek LLM 67B DeepSeek

24.8

Rank #341 Confirmed

Phi-3.5-MoE Microsoft

—

Unranked

Side by side

DeepSeek LLM 67BPhi-3.5-MoE
ProviderDeepSeekMicrosoft
Noometry Index24.8—
Released2023-11-292024-08-17
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked153

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

Category by category

Coding Not comparable

DeepSeek LLM 67B: 31.3 (#273), Phi-3.5-MoE: —

BenchmarkDeepSeek LLM 67BPhi-3.5-MoE
LMArena Coding1096—

Reasoning Not comparable

DeepSeek LLM 67B: 15.9 (#300), Phi-3.5-MoE: —

BenchmarkDeepSeek LLM 67BPhi-3.5-MoE
Chess Puzzles0%—
LMArena Hard Prompts1070—
Epoch Capabilities Index110.54—
PIQA—88.6%

Math Not comparable

DeepSeek LLM 67B: 8.1 (#318), Phi-3.5-MoE: —

BenchmarkDeepSeek LLM 67BPhi-3.5-MoE
OTIS Mock AIME 2024-20250.8%—
LMArena Math1108—
MATH Level 56.4%—
GSM8K—88.7%

Knowledge Not comparable

DeepSeek LLM 67B: 7.1 (#308), Phi-3.5-MoE: —

BenchmarkDeepSeek LLM 67BPhi-3.5-MoE
GPQA Diamond24.6%—
BoolQ—84.6%

Multilingual Not comparable

DeepSeek LLM 67B: 29.5 (#262), Phi-3.5-MoE: —

BenchmarkDeepSeek LLM 67BPhi-3.5-MoE
LMArena Non-English1073—
LMArena Chinese1132—

Instruction Following Not comparable

DeepSeek LLM 67B: 55.7 (#272), Phi-3.5-MoE: —

BenchmarkDeepSeek LLM 67BPhi-3.5-MoE
LMArena Instruction Following1079—

Long Context Not comparable

DeepSeek LLM 67B: 33.1 (#260), Phi-3.5-MoE: —

BenchmarkDeepSeek LLM 67BPhi-3.5-MoE
LMArena Longer Query1092—

Writing & Preference Not comparable

DeepSeek LLM 67B: 31.8 (#277), Phi-3.5-MoE: —

BenchmarkDeepSeek LLM 67BPhi-3.5-MoE
LMArena Text1105—
LMArena Creative Writing1067—
LMArena Multi-Turn1082—

Frequently asked questions

Is DeepSeek LLM 67B better than Phi-3.5-MoE?

DeepSeek LLM 67B has enough public results to be ranked (#341); Phi-3.5-MoE does not yet, so treat this comparison as directional.

How many benchmarks do DeepSeek LLM 67B and Phi-3.5-MoE share?

0 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Phi-3.5-MoE has 3.

Related comparisons

Go deeper