Noometry

Model comparison

Claude 3 Haiku vs DeepSeek-V3.1

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 25.7 on the Noometry Index.

Last verified . 24 shared benchmarks.

Claude 3 Haiku Anthropic

25.7

Rank #333 Confirmed

DeepSeek-V3.1 DeepSeek

42.2

Rank #106 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and DeepSeek-V3.1 in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.5 to 29.8.
  • The biggest single-benchmark swing is DTBench: 50.1% for Claude 3 Haiku and 82.7% for DeepSeek-V3.1.
  • DeepSeek-V3.1 has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuDeepSeek-V3.1
ProviderAnthropicDeepSeek
Noometry Index25.742.2
Released2024-03-072025-08-21
WeightsProprietaryOpen
Context window—164K
Max output—8K
Input $ / M tokens—$0.25
Output $ / M tokens—$0.95
Results tracked3727

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

Category by category

Coding DeepSeek-V3.1 leads

Claude 3 Haiku: 26.1 (#320), DeepSeek-V3.1: 39.8 (#140)

BenchmarkClaude 3 HaikuDeepSeek-V3.1
WeirdML9.8%38.4%
LMArena Coding11991417
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning DeepSeek-V3.1 leads

Claude 3 Haiku: 15.7 (#303), DeepSeek-V3.1: 27.3 (#109)

BenchmarkClaude 3 HaikuDeepSeek-V3.1
Kagi LLM Benchmark34.2%53.2%
LMArena Hard Prompts11741417
DTBench50.1%82.7%
LMCA8.8%24.3%
Epoch Capabilities Index118.3139.92
ForecastBench53.258
SimpleBench—40%
WinoGrande74.2%—

Math DeepSeek-V3.1 leads

Claude 3 Haiku: 9.2 (#313), DeepSeek-V3.1: 36.1 (#125)

BenchmarkClaude 3 HaikuDeepSeek-V3.1
LMArena Math11881420
OTIS Mock AIME 2024-20251.8%—
MATH Level 514.9%—

Knowledge DeepSeek-V3.1 leads

Claude 3 Haiku: 17.3 (#280), DeepSeek-V3.1: 43.0 (#86)

BenchmarkClaude 3 HaikuDeepSeek-V3.1
LMArena Expert11481403
GPQA Diamond36.3%—
Confabulations34.2%—
Vectara Hallucination Rate—5.5%
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.1 (#123), DeepSeek-V3.1: —

BenchmarkClaude 3 HaikuDeepSeek-V3.1
LMArena Vision950—
ScienceQA72%—

Multilingual DeepSeek-V3.1 leads

Claude 3 Haiku: 36.1 (#238), DeepSeek-V3.1: 51.8 (#100)

BenchmarkClaude 3 HaikuDeepSeek-V3.1
LMArena Non-English11781400
LMArena Chinese11551470
LMArena French11941447
LMArena German11741412
LMArena Japanese11021374
LMArena Korean11081337
LMArena Russian12041405
LMArena Spanish11651429

Instruction Following DeepSeek-V3.1 leads

Claude 3 Haiku: 61.5 (#242), DeepSeek-V3.1: 74.1 (#105)

BenchmarkClaude 3 HaikuDeepSeek-V3.1
LMArena Instruction Following11741400

Long Context Too close to call

Claude 3 Haiku: 36.1 (#232), DeepSeek-V3.1: 36.3 (#227)

BenchmarkClaude 3 HaikuDeepSeek-V3.1
LMArena Longer Query11911422
Fiction.LiveBench—52.8%

Writing & Preference DeepSeek-V3.1 leads

Claude 3 Haiku: 29.8 (#286), DeepSeek-V3.1: 60.5 (#93)

BenchmarkClaude 3 HaikuDeepSeek-V3.1
LMArena Text11951420
LMArena Creative Writing11571401
EQ-Bench Creative Writing7171436
LMArena Multi-Turn11901408

Frequently asked questions

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

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 25.7 on the Noometry Index.

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

DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 26.1 in the Noometry coding category.

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

24 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and DeepSeek-V3.1 has 27.

Related comparisons

Go deeper