Noometry

Model comparison

DeepSeek-V3.1 vs Llama 3.1-70B

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 29.4 on the Noometry Index.

Last verified . 22 shared benchmarks.

DeepSeek-V3.1 DeepSeek

42.2

Rank #106 Confirmed

Llama 3.1-70B Meta

29.4

Rank #299 Confirmed

Summary

  • They share 22 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Llama 3.1-70B in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.5 to 35.6.
  • The biggest single-benchmark swing is WeirdML: 38.4% for DeepSeek-V3.1 and 9% for Llama 3.1-70B.
  • Llama 3.1-70B is cheaper at $0.40 / $0.40 per million input/output tokens, against $0.25 / $0.95 for DeepSeek-V3.1.
  • DeepSeek-V3.1 accepts more context: 164K tokens versus 128K.

Side by side

DeepSeek-V3.1Llama 3.1-70B
ProviderDeepSeekMeta
Noometry Index42.229.4
Released2025-08-212024-07-23
WeightsOpenOpen
Context window164K128K
Max output8K4K
Input $ / M tokens$0.25$0.40
Output $ / M tokens$0.95$0.40
Results tracked2735

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

Category by category

Coding DeepSeek-V3.1 leads

DeepSeek-V3.1: 39.8 (#140), Llama 3.1-70B: 29.8 (#292)

BenchmarkDeepSeek-V3.1Llama 3.1-70B
WeirdML38.4%9%
LMArena Coding14171260
BigCodeBench Instruct—46.1%
BigCodeBench Complete—54.8%

Agentic & Tool Use Not comparable

DeepSeek-V3.1: —, Llama 3.1-70B: 24.9 (#104)

BenchmarkDeepSeek-V3.1Llama 3.1-70B
TheAgentCompany—6.9%
BALROG—27.9%

Reasoning DeepSeek-V3.1 leads

DeepSeek-V3.1: 27.3 (#109), Llama 3.1-70B: 20.8 (#215)

BenchmarkDeepSeek-V3.1Llama 3.1-70B
LMArena Hard Prompts14171241
DTBench82.7%60%
LMCA24.3%14.8%
Epoch Capabilities Index139.92125.91
SimpleBench40%—
Kagi LLM Benchmark53.2%—
ForecastBench58—

Math DeepSeek-V3.1 leads

DeepSeek-V3.1: 36.1 (#125), Llama 3.1-70B: 12.7 (#298)

BenchmarkDeepSeek-V3.1Llama 3.1-70B
LMArena Math14201252
OTIS Mock AIME 2024-2025—3.6%
Omni-MATH—21%
MATH Level 5—36.7%

Knowledge DeepSeek-V3.1 leads

DeepSeek-V3.1: 43.0 (#86), Llama 3.1-70B: 24.1 (#264)

BenchmarkDeepSeek-V3.1Llama 3.1-70B
LMArena Expert14031209
GPQA Diamond—44.2%
MMLU-Pro—65.3%
Vectara Hallucination Rate5.5%—
GPQA (HELM)—42.6%
MMLU—80.1%

Multilingual DeepSeek-V3.1 leads

DeepSeek-V3.1: 51.8 (#100), Llama 3.1-70B: 38.9 (#220)

BenchmarkDeepSeek-V3.1Llama 3.1-70B
LMArena Non-English14001219
LMArena Chinese14701215
LMArena French14471260
LMArena German14121222
LMArena Japanese13741132
LMArena Korean13371140
LMArena Russian14051234
LMArena Spanish14291253

Instruction Following DeepSeek-V3.1 leads

DeepSeek-V3.1: 74.1 (#105), Llama 3.1-70B: 65.5 (#218)

BenchmarkDeepSeek-V3.1Llama 3.1-70B
LMArena Instruction Following14001231
IFEval—82.1%

Long Context Llama 3.1-70B leads

DeepSeek-V3.1: 36.3 (#227), Llama 3.1-70B: 37.6 (#208)

BenchmarkDeepSeek-V3.1Llama 3.1-70B
LMArena Longer Query14221241
Fiction.LiveBench52.8%—

Writing & Preference DeepSeek-V3.1 leads

DeepSeek-V3.1: 60.5 (#93), Llama 3.1-70B: 35.6 (#262)

BenchmarkDeepSeek-V3.1Llama 3.1-70B
LMArena Text14201261
LMArena Creative Writing14011232
EQ-Bench Creative Writing1436784
LMArena Multi-Turn14081256
WildBench—75.8%

Frequently asked questions

Is DeepSeek-V3.1 better than Llama 3.1-70B?

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 29.4 on the Noometry Index.

Which is cheaper, DeepSeek-V3.1 or Llama 3.1-70B?

Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; DeepSeek-V3.1 lists at $0.25 and $0.95.

Is DeepSeek-V3.1 or Llama 3.1-70B better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 29.8 in the Noometry coding category.

Which has the bigger context window?

DeepSeek-V3.1 does, with 164K tokens against 128K.

How many benchmarks do DeepSeek-V3.1 and Llama 3.1-70B share?

22 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Llama 3.1-70B has 35.

Related comparisons

Go deeper