Noometry

Model comparison

DeepSeek-V2.5 (Sep 2024) vs Llama 3.2 3B

DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 28.9 on the Noometry Index.

Last verified . 15 shared benchmarks.

DeepSeek-V2.5 (Sep 2024) DeepSeek

37.6

Rank #200 Confirmed

Llama 3.2 3B Meta

28.9

Rank #321 Confirmed

Summary

  • They share 15 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 8 categories and Llama 3.2 3B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where DeepSeek-V2.5 (Sep 2024) leads 49.8 to 24.7.
  • The biggest single-benchmark swing is BigCodeBench Instruct: 48.6% for DeepSeek-V2.5 (Sep 2024) and 23.4% for Llama 3.2 3B.

Side by side

DeepSeek-V2.5 (Sep 2024)Llama 3.2 3B
ProviderDeepSeekMeta
Noometry Index37.628.9
Released2024-09-062024-09-24
WeightsOpenOpen
Context window—131K
Max output—118K
Input $ / M tokens—$0.05
Output $ / M tokens—$0.33
Results tracked2218

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

Category by category

Coding DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Llama 3.2 3B: 27.6 (#319)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 3B
BigCodeBench Instruct48.6%23.4%
LMArena Coding13091098
BigCodeBench Complete53.2%28.3%
Aider Polyglot17.8%—
HumanEval+83.5%—
MBPP+74.1%—

Agentic & Tool Use Not comparable

DeepSeek-V2.5 (Sep 2024): —, Llama 3.2 3B: 20.1 (#143)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 3B
Berkeley Function Calling Leaderboard—21.9%
BALROG—10.1%

Reasoning DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Llama 3.2 3B: 21.0 (#228)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 3B
LMArena Hard Prompts12891095

Math DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Llama 3.2 3B: 32.4 (#214)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 3B
LMArena Math12881126

Knowledge DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Llama 3.2 3B: 29.7 (#235)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 3B
LMArena Expert12661090

Multilingual DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Llama 3.2 3B: 26.2 (#281)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 3B
LMArena Non-English12731019
LMArena Chinese13181017
LMArena German12581056
LMArena Russian1289949
LMArena French1289—
LMArena Japanese1228—
LMArena Korean1209—
LMArena Spanish1248—

Instruction Following DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Llama 3.2 3B: 56.0 (#275)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 3B
LMArena Instruction Following12801089

Long Context DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Llama 3.2 3B: 33.4 (#261)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 3B
LMArena Longer Query13011100

Writing & Preference DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Llama 3.2 3B: 24.7 (#307)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 3B
LMArena Text12941110
LMArena Creative Writing12851094
LMArena Multi-Turn12971105
EQ-Bench Creative Writing—595

Frequently asked questions

Is DeepSeek-V2.5 (Sep 2024) better than Llama 3.2 3B?

DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 28.9 on the Noometry Index.

Is DeepSeek-V2.5 (Sep 2024) or Llama 3.2 3B better for coding?

DeepSeek-V2.5 (Sep 2024) scores higher on coding benchmarks: 31.7 versus 27.6 in the Noometry coding category.

How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Llama 3.2 3B share?

15 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Llama 3.2 3B has 18.

Related comparisons

Go deeper