Noometry

Model comparison

Claude 3 Haiku vs DeepSeek-V3.2-Speciale

DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.7 to 25.9 on the Noometry Index.

Last verified . 2 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

DeepSeek-V3.2-Speciale DeepSeek

39.7

Rank #162 Reported

Summary

  • They share 2 benchmarks with published results for both. Claude 3 Haiku 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 16.3.
  • The biggest single-benchmark swing is WeirdML: 9.8% for Claude 3 Haiku 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 HaikuDeepSeek-V3.2-Speciale
ProviderAnthropicDeepSeek
Noometry Index25.939.7
Released2024-03-072025-12-01
WeightsProprietaryOpen
Context window—128K
Max output—128K
Input $ / M tokens—$0.58
Output $ / M tokens—$1.68
Results tracked373

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

Category by category

Coding DeepSeek-V3.2-Speciale leads

Claude 3 Haiku: 26.4 (#325), DeepSeek-V3.2-Speciale: 40.4 (#140)

BenchmarkClaude 3 HaikuDeepSeek-V3.2-Speciale
WeirdML9.8%46.7%
BigCodeBench Instruct39.4%—
LMArena Coding1199—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning DeepSeek-V3.2-Speciale leads

Claude 3 Haiku: 16.3 (#307), DeepSeek-V3.2-Speciale: 32.9 (#73)

BenchmarkClaude 3 HaikuDeepSeek-V3.2-Speciale
SimpleBench—52.6%
Kagi LLM Benchmark34.2%—
LMArena Hard Prompts1174—
DTBench50.1%—
LMCA8.8%—
Epoch Capabilities Index118.35—
ForecastBench53.2—
WinoGrande74.2%—

Math Not comparable

Claude 3 Haiku: 9.8 (#319), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3 HaikuDeepSeek-V3.2-Speciale
OTIS Mock AIME 2024-20251.8%—
LMArena Math1188—
MATH Level 514.9%—

Knowledge Not comparable

Claude 3 Haiku: 17.3 (#285), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3 HaikuDeepSeek-V3.2-Speciale
GPQA Diamond36.3%—
Confabulations34.2%—
LMArena Expert1148—
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3 HaikuDeepSeek-V3.2-Speciale
LMArena Vision950—
ScienceQA72%—

Multilingual Not comparable

Claude 3 Haiku: 36.0 (#243), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3 HaikuDeepSeek-V3.2-Speciale
LMArena Non-English1178—
LMArena Chinese1155—
LMArena French1195—
LMArena German1174—
LMArena Japanese1102—
LMArena Korean1109—
LMArena Russian1204—
LMArena Spanish1166—

Instruction Following Not comparable

Claude 3 Haiku: 61.3 (#247), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3 HaikuDeepSeek-V3.2-Speciale
LMArena Instruction Following1173—

Long Context Not comparable

Claude 3 Haiku: 36.1 (#237), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3 HaikuDeepSeek-V3.2-Speciale
LMArena Longer Query1190—

Writing & Preference DeepSeek-V3.2-Speciale leads

Claude 3 Haiku: 29.7 (#291), DeepSeek-V3.2-Speciale: 46.0 (#222)

BenchmarkClaude 3 HaikuDeepSeek-V3.2-Speciale
EQ-Bench Creative Writing7171276
LMArena Text1195—
LMArena Creative Writing1157—
LMArena Multi-Turn1190—

Frequently asked questions

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

DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.7 to 25.9 on the Noometry Index.

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

DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 40.4 versus 26.4 in the Noometry coding category.

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

2 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and DeepSeek-V3.2-Speciale has 3.

Related comparisons

Go deeper