Noometry

Model comparison

Claude 3 Sonnet vs DeepSeek-V3.2-Exp

DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 29.0 on the Noometry Index.

Last verified . 22 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

DeepSeek-V3.2-Exp DeepSeek

44.3

Rank #78 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and DeepSeek-V3.2-Exp in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek-V3.2-Exp leads 41.7 to 10.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 87.8% for DeepSeek-V3.2-Exp.
  • DeepSeek-V3.2-Exp has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetDeepSeek-V3.2-Exp
ProviderAnthropicDeepSeek
Noometry Index29.044.3
Released2024-02-292025-09-29
WeightsProprietaryOpen
Context window—164K
Max output—66K
Input $ / M tokens—$0.26
Output $ / M tokens—$0.38
Results tracked3049

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

Category by category

Coding DeepSeek-V3.2-Exp leads

Claude 3 Sonnet: 29.6 (#302), DeepSeek-V3.2-Exp: 46.5 (#65)

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Exp
WeirdML10.2%39.5%
LMArena Coding12231454
SWE-bench Verified (bash only)—70%
Aider Polyglot—74.2%
LMArena WebDev—1362
SWE-bench Multilingual—59%
SciCode—38.9%
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, DeepSeek-V3.2-Exp: 32.7 (#59)

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Exp
Terminal-Bench—39.6%
APEX-Agents—21.3%
Berkeley Function Calling Leaderboard—56.7%
TheAgentCompany—42.9%
Vending-Bench 2—1,034

Reasoning DeepSeek-V3.2-Exp leads

Claude 3 Sonnet: 20.5 (#237), DeepSeek-V3.2-Exp: 22.1 (#208)

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Exp
LMArena Hard Prompts11971434
DTBench53.6%87.7%
Epoch Capabilities Index120.7146.27
ARC-AGI-2—4%
Kagi LLM Benchmark—52.2%
NYT Connections (extended)—36.7%
ARC-AGI-1—57%
CritPt—2.9%
Chess Puzzles—14%
Thematic Generalization—65%
LMCA—29.1%
WinoGrande75.1%—

Math DeepSeek-V3.2-Exp leads

Claude 3 Sonnet: 10.7 (#310), DeepSeek-V3.2-Exp: 41.7 (#87)

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Exp
OTIS Mock AIME 2024-20252.5%87.8%
LMArena Math12131435
MathArena Final-Answer Competitions—57.7%
ProofBench—8%
MATH Level 518.2%—
FrontierMath (Feb 2025 set)—22.1%
FrontierMath Tier 4 (v1)—2.1%

Knowledge DeepSeek-V3.2-Exp leads

Claude 3 Sonnet: 21.1 (#276), DeepSeek-V3.2-Exp: 51.7 (#66)

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Exp
GPQA Diamond40.6%83.4%
LMArena Expert11731436
Vectara Hallucination Rate—5.3%
MMLU75.9%—

Multimodal Not comparable

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

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

Multilingual DeepSeek-V3.2-Exp leads

Claude 3 Sonnet: 37.8 (#234), DeepSeek-V3.2-Exp: 52.2 (#90)

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Exp
LMArena Non-English12051409
LMArena Chinese11891461
LMArena French12291433
LMArena German12041440
LMArena Japanese11311374
LMArena Korean11281371
LMArena Russian12271424
LMArena Spanish12041440

Instruction Following DeepSeek-V3.2-Exp leads

Claude 3 Sonnet: 62.8 (#235), DeepSeek-V3.2-Exp: 74.5 (#93)

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Exp
LMArena Instruction Following11991413

Long Context DeepSeek-V3.2-Exp leads

Claude 3 Sonnet: 36.7 (#228), DeepSeek-V3.2-Exp: 47.6 (#16)

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Exp
LMArena Longer Query12111428
Fiction.LiveBench—83.3%
CL-bench—13.2%
CL-bench Life—9.5%

Writing & Preference DeepSeek-V3.2-Exp leads

Claude 3 Sonnet: 42.1 (#238), DeepSeek-V3.2-Exp: 62.4 (#77)

BenchmarkClaude 3 SonnetDeepSeek-V3.2-Exp
LMArena Text12181425
LMArena Creative Writing11861403
LMArena Multi-Turn12271427
EQ-Bench Creative Writing—1515

Frequently asked questions

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

DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 29.0 on the Noometry Index.

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

DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 29.6 in the Noometry coding category.

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

22 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and DeepSeek-V3.2-Exp has 49.

Related comparisons

Go deeper