Noometry

Model comparison

Claude 3 Sonnet vs DeepSeek-V3.1

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 29.0 on the Noometry Index.

Last verified . 20 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

DeepSeek-V3.1 DeepSeek

42.8

Rank #108 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Claude 3 Sonnet scores higher in 1 category and DeepSeek-V3.1 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek-V3.1 leads 38.9 to 10.7.
  • The biggest single-benchmark swing is DTBench: 53.6% for Claude 3 Sonnet and 82.7% for DeepSeek-V3.1.
  • DeepSeek-V3.1 has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetDeepSeek-V3.1
ProviderAnthropicDeepSeek
Noometry Index29.042.8
Released2024-02-292025-08-21
WeightsProprietaryOpen
Context window—164K
Max output—8K
Input $ / M tokens—$0.25
Output $ / M tokens—$0.95
Results tracked3027

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

Category by category

Coding DeepSeek-V3.1 leads

Claude 3 Sonnet: 29.6 (#302), DeepSeek-V3.1: 40.3 (#144)

BenchmarkClaude 3 SonnetDeepSeek-V3.1
WeirdML10.2%38.4%
LMArena Coding12231417
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
HumanEval+64%—
MBPP+69.3%—

Reasoning DeepSeek-V3.1 leads

Claude 3 Sonnet: 20.5 (#237), DeepSeek-V3.1: 27.9 (#110)

BenchmarkClaude 3 SonnetDeepSeek-V3.1
LMArena Hard Prompts11971417
DTBench53.6%82.7%
Epoch Capabilities Index120.7139.92
SimpleBench—40%
Kagi LLM Benchmark—53.2%
LMCA—24.3%
ForecastBench—58
WinoGrande75.1%—

Math DeepSeek-V3.1 leads

Claude 3 Sonnet: 10.7 (#310), DeepSeek-V3.1: 38.9 (#122)

BenchmarkClaude 3 SonnetDeepSeek-V3.1
LMArena Math12131420
OTIS Mock AIME 2024-20252.5%—
MATH Level 518.2%—

Knowledge DeepSeek-V3.1 leads

Claude 3 Sonnet: 21.1 (#276), DeepSeek-V3.1: 43.7 (#90)

BenchmarkClaude 3 SonnetDeepSeek-V3.1
LMArena Expert11731405
GPQA Diamond40.6%—
Vectara Hallucination Rate—5.5%
MMLU75.9%—

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), DeepSeek-V3.1: —

BenchmarkClaude 3 SonnetDeepSeek-V3.1
LMArena Vision984—

Multilingual DeepSeek-V3.1 leads

Claude 3 Sonnet: 37.8 (#234), DeepSeek-V3.1: 51.6 (#106)

BenchmarkClaude 3 SonnetDeepSeek-V3.1
LMArena Non-English12051400
LMArena Chinese11891469
LMArena French12291447
LMArena German12041411
LMArena Japanese11311378
LMArena Korean11281337
LMArena Russian12271405
LMArena Spanish12041431

Instruction Following DeepSeek-V3.1 leads

Claude 3 Sonnet: 62.8 (#235), DeepSeek-V3.1: 73.9 (#110)

BenchmarkClaude 3 SonnetDeepSeek-V3.1
LMArena Instruction Following11991400

Long Context Too close to call

Claude 3 Sonnet: 36.7 (#228), DeepSeek-V3.1: 36.3 (#232)

BenchmarkClaude 3 SonnetDeepSeek-V3.1
LMArena Longer Query12111422
Fiction.LiveBench—52.8%

Writing & Preference DeepSeek-V3.1 leads

Claude 3 Sonnet: 42.1 (#238), DeepSeek-V3.1: 60.3 (#98)

BenchmarkClaude 3 SonnetDeepSeek-V3.1
LMArena Text12181420
LMArena Creative Writing11861401
LMArena Multi-Turn12271408
EQ-Bench Creative Writing—1436

Frequently asked questions

Is Claude 3 Sonnet better than DeepSeek-V3.1?

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or DeepSeek-V3.1 better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and DeepSeek-V3.1 share?

20 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and DeepSeek-V3.1 has 27.

Related comparisons

Go deeper