Noometry

Model comparison

DeepSeek-V2.5 (Sep 2024) vs Llama 3.2 1B

DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 20.1 on the Noometry Index.

Last verified . 15 shared benchmarks.

DeepSeek-V2.5 (Sep 2024) DeepSeek

37.6

Rank #200 Confirmed

Llama 3.2 1B Meta

20.1

Rank #354 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 1B 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 21.3.
  • The biggest single-benchmark swing is BigCodeBench Complete: 53.2% for DeepSeek-V2.5 (Sep 2024) and 11.3% for Llama 3.2 1B.

Side by side

DeepSeek-V2.5 (Sep 2024)Llama 3.2 1B
ProviderDeepSeekMeta
Noometry Index37.620.1
Released2024-09-062024-09-24
WeightsOpenOpen
Context window—60K
Max output—54K
Input $ / M tokens—$0.027
Output $ / M tokens—$0.20
Results tracked2222

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 1B: 21.1 (#338)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 1B
BigCodeBench Instruct48.6%8.2%
LMArena Coding13091070
BigCodeBench Complete53.2%11.3%
Aider Polyglot17.8%—
HumanEval+83.5%—
MBPP+74.1%—

Agentic & Tool Use Not comparable

DeepSeek-V2.5 (Sep 2024): —, Llama 3.2 1B: 14.6 (#150)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 1B
Berkeley Function Calling Leaderboard—10.8%
BALROG—6.6%

Reasoning DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Llama 3.2 1B: 16.2 (#308)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 1B
LMArena Hard Prompts12891044
Chess Puzzles—0%
Epoch Capabilities Index—101.99

Math DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Llama 3.2 1B: 10.4 (#313)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 1B
LMArena Math12881086
OTIS Mock AIME 2024-2025—0.6%

Knowledge DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Llama 3.2 1B: 7.2 (#312)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 1B
LMArena Expert12661007
GPQA Diamond—23.9%

Multilingual DeepSeek-V2.5 (Sep 2024) leads

DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Llama 3.2 1B: 23.8 (#292)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 1B
LMArena Non-English1273973
LMArena Chinese1318959
LMArena German12581014
LMArena Russian1289941
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 1B: 52.4 (#290)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 1B
LMArena Instruction Following12801031

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

DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Llama 3.2 1B: 31.9 (#274)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 1B
LMArena Longer Query13011050

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

DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Llama 3.2 1B: 21.3 (#310)

BenchmarkDeepSeek-V2.5 (Sep 2024)Llama 3.2 1B
LMArena Text12941055
LMArena Creative Writing12851033
LMArena Multi-Turn12971030
EQ-Bench Creative Writing—200

Frequently asked questions

Is DeepSeek-V2.5 (Sep 2024) better than Llama 3.2 1B?

DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 20.1 on the Noometry Index.

Is DeepSeek-V2.5 (Sep 2024) or Llama 3.2 1B better for coding?

DeepSeek-V2.5 (Sep 2024) scores higher on coding benchmarks: 31.7 versus 21.1 in the Noometry coding category.

How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Llama 3.2 1B share?

15 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Llama 3.2 1B has 22.

Related comparisons

Go deeper