Noometry

Model comparison

Claude 3.5 Haiku vs DeepSeek-V3.2-Speciale

DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.7 to 29.2 on the Noometry Index.

Last verified . 2 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

DeepSeek-V3.2-Speciale DeepSeek

39.7

Rank #162 Reported

Summary

  • They share 2 benchmarks with published results for both. Claude 3.5 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 17.7.
  • The biggest single-benchmark swing is WeirdML: 30.7% for Claude 3.5 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 3.5 HaikuDeepSeek-V3.2-Speciale
ProviderAnthropicDeepSeek
Noometry Index29.239.7
Released2024-10-222025-12-01
WeightsProprietaryOpen
Context window—128K
Max output—128K
Input $ / M tokens—$0.58
Output $ / M tokens—$1.68
Results tracked493

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

Category by category

Coding DeepSeek-V3.2-Speciale leads

Claude 3.5 Haiku: 32.9 (#265), DeepSeek-V3.2-Speciale: 40.4 (#140)

BenchmarkClaude 3.5 HaikuDeepSeek-V3.2-Speciale
WeirdML30.7%46.7%
Aider Polyglot28%—
SciCode27.4%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
LMArena Coding1286—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 28.0 (#95), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3.5 HaikuDeepSeek-V3.2-Speciale
BALROG19.3%—

Reasoning DeepSeek-V3.2-Speciale leads

Claude 3.5 Haiku: 17.7 (#290), DeepSeek-V3.2-Speciale: 32.9 (#73)

BenchmarkClaude 3.5 HaikuDeepSeek-V3.2-Speciale
SimpleBench—52.6%
CritPt0%—
LiveBench Reasoning28.1%—
LMArena Hard Prompts1251—
DTBench56.7%—
LiveBench Data Analysis48.5%—
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math Not comparable

Claude 3.5 Haiku: 14.7 (#300), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3.5 HaikuDeepSeek-V3.2-Speciale
OTIS Mock AIME 2024-20254.3%—
Omni-MATH22.4%—
LiveBench Math35.5%—
LMArena Math1244—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Not comparable

Claude 3.5 Haiku: 18.7 (#281), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3.5 HaikuDeepSeek-V3.2-Speciale
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
GPQA (HELM)36.3%—
LMArena Expert1208—
MMLU74.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.8 (#117), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3.5 HaikuDeepSeek-V3.2-Speciale
LMArena Vision1092—
GeoBench34%—

Multilingual Not comparable

Claude 3.5 Haiku: 40.0 (#218), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3.5 HaikuDeepSeek-V3.2-Speciale
LMArena Non-English1238—
LMArena Chinese1229—
LMArena French1264—
LMArena German1237—
LMArena Japanese1175—
LMArena Korean1173—
LMArena Russian1253—
LMArena Spanish1261—

Instruction Following Not comparable

Claude 3.5 Haiku: 62.9 (#234), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3.5 HaikuDeepSeek-V3.2-Speciale
LiveBench Instruction Following61.9%—
IFEval79.2%—
LMArena Instruction Following1241—

Long Context Not comparable

Claude 3.5 Haiku: 38.3 (#200), DeepSeek-V3.2-Speciale: —

BenchmarkClaude 3.5 HaikuDeepSeek-V3.2-Speciale
LMArena Longer Query1261—

Writing & Preference DeepSeek-V3.2-Speciale leads

Claude 3.5 Haiku: 42.7 (#234), DeepSeek-V3.2-Speciale: 46.0 (#222)

BenchmarkClaude 3.5 HaikuDeepSeek-V3.2-Speciale
EQ-Bench Creative Writing11461276
LMArena Text1255—
LMArena Creative Writing1233—
Short-Story Creative Writing73.5%—
WildBench76%—
LMArena Multi-Turn1265—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than DeepSeek-V3.2-Speciale?

DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.7 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or DeepSeek-V3.2-Speciale better for coding?

DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 40.4 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and DeepSeek-V3.2-Speciale share?

2 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and DeepSeek-V3.2-Speciale has 3.

Related comparisons

Go deeper