Noometry

Model comparison

Claude 3 Sonnet vs DeepSeek-V3.2-Speciale

DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.7 to 29.0 on the Noometry Index.

Last verified . 1 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

DeepSeek-V3.2-Speciale DeepSeek

39.7

Rank #162 Reported

Summary

  • They share 1 benchmark with published results for both. Claude 3 Sonnet scores higher in 0 categories and DeepSeek-V3.2-Speciale in 3 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek-V3.2-Speciale leads 32.9 to 20.5.
  • The biggest single-benchmark swing is WeirdML: 10.2% for Claude 3 Sonnet and 46.7% for DeepSeek-V3.2-Speciale.
  • DeepSeek-V3.2-Speciale has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetDeepSeek-V3.2-Speciale
ProviderAnthropicDeepSeek
Noometry Index29.039.7
Released2024-02-292025-12-01
WeightsProprietaryOpen
Context window—128K
Max output—128K
Input $ / M tokens—$0.58
Output $ / M tokens—$1.68
Results tracked303

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

Category by category

Coding DeepSeek-V3.2-Speciale leads

Claude 3 Sonnet: 29.6 (#302), DeepSeek-V3.2-Speciale: 40.4 (#140)

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Speciale
WeirdML10.2%46.7%
BigCodeBench Instruct42.7%—
LMArena Coding1223—
BigCodeBench Complete53.8%—
HumanEval+64%—
MBPP+69.3%—

Reasoning DeepSeek-V3.2-Speciale leads

Claude 3 Sonnet: 20.5 (#237), DeepSeek-V3.2-Speciale: 32.9 (#73)

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Speciale
SimpleBench—52.6%
LMArena Hard Prompts1197—
DTBench53.6%—
Epoch Capabilities Index120.7—
WinoGrande75.1%—

Math Not comparable

Claude 3 Sonnet: 10.7 (#310), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Speciale
OTIS Mock AIME 2024-20252.5%—
LMArena Math1213—
MATH Level 518.2%—

Knowledge Not comparable

Claude 3 Sonnet: 21.1 (#276), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Speciale
GPQA Diamond40.6%—
LMArena Expert1173—
MMLU75.9%—

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Speciale
LMArena Vision984—

Multilingual Not comparable

Claude 3 Sonnet: 37.8 (#234), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Speciale
LMArena Non-English1205—
LMArena Chinese1189—
LMArena French1229—
LMArena German1204—
LMArena Japanese1131—
LMArena Korean1128—
LMArena Russian1227—
LMArena Spanish1204—

Instruction Following Not comparable

Claude 3 Sonnet: 62.8 (#235), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Speciale
LMArena Instruction Following1199—

Long Context Not comparable

Claude 3 Sonnet: 36.7 (#228), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Speciale
LMArena Longer Query1211—

Writing & Preference DeepSeek-V3.2-Speciale leads

Claude 3 Sonnet: 42.1 (#238), DeepSeek-V3.2-Speciale: 46.0 (#222)

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Speciale
LMArena Text1218—
LMArena Creative Writing1186—
EQ-Bench Creative Writing—1276
LMArena Multi-Turn1227—

Frequently asked questions

Is Claude 3 Sonnet better than DeepSeek-V3.2-Speciale?

DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.7 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or DeepSeek-V3.2-Speciale better for coding?

DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 40.4 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and DeepSeek-V3.2-Speciale share?

1 benchmark has published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and DeepSeek-V3.2-Speciale has 3.

Related comparisons

Go deeper