Noometry

Model comparison

Claude 3 Haiku vs DeepSeek Coder 6.7B

Claude 3 Haiku has enough public results to be ranked (#333); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

Last verified . 7 shared benchmarks.

Claude 3 Haiku Anthropic

25.7

Rank #333 Confirmed

DeepSeek Coder 6.7B DeepSeek

37.1

Unranked Sparse

Summary

  • They share 7 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and DeepSeek Coder 6.7B in 1 category; one gap is clear of the uncertainty.
  • The widest gap is in coding, where DeepSeek Coder 6.7B leads 35.2 to 26.1.
  • The biggest single-benchmark swing is BigCodeBench Complete: 50.1% for Claude 3 Haiku and 43.8% for DeepSeek Coder 6.7B.
  • DeepSeek Coder 6.7B has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuDeepSeek Coder 6.7B
ProviderAnthropicDeepSeek
Noometry Index25.737.1
Released2024-03-072023-11-02
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked379

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

Category by category

Coding DeepSeek Coder 6.7B leads

Claude 3 Haiku: 26.1 (#320), DeepSeek Coder 6.7B: 35.2 (#216)

BenchmarkClaude 3 HaikuDeepSeek Coder 6.7B
BigCodeBench Instruct39.4%35.5%
BigCodeBench Complete50.1%43.8%
HumanEval+68.9%71.3%
MBPP+68.8%65.6%
WeirdML9.8%—
LMArena Coding1199—
CadEval12%—

Reasoning Not comparable

Claude 3 Haiku: 15.7 (#303), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 HaikuDeepSeek Coder 6.7B
Epoch Capabilities Index118.388.88
WinoGrande74.2%57.6%
Kagi LLM Benchmark34.2%—
LMArena Hard Prompts1174—
DTBench50.1%—
LMCA8.8%—
ForecastBench53.2—

Math Not comparable

Claude 3 Haiku: 9.2 (#313), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 HaikuDeepSeek Coder 6.7B
OTIS Mock AIME 2024-20251.8%—
LMArena Math1188—
MATH Level 514.9%—
GSM8K—21.3%

Knowledge Not comparable

Claude 3 Haiku: 17.3 (#280), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 HaikuDeepSeek Coder 6.7B
MMLU73.8%36.4%
GPQA Diamond36.3%—
Confabulations34.2%—
LMArena Expert1148—
ARC (AI2) Challenge—36.4%

Multimodal Not comparable

Claude 3 Haiku: 23.1 (#123), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 HaikuDeepSeek Coder 6.7B
LMArena Vision950—
ScienceQA72%—

Multilingual Not comparable

Claude 3 Haiku: 36.1 (#238), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 HaikuDeepSeek Coder 6.7B
LMArena Non-English1178—
LMArena Chinese1155—
LMArena French1194—
LMArena German1174—
LMArena Japanese1102—
LMArena Korean1108—
LMArena Russian1204—
LMArena Spanish1165—

Instruction Following Not comparable

Claude 3 Haiku: 61.5 (#242), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 HaikuDeepSeek Coder 6.7B
LMArena Instruction Following1174—

Long Context Not comparable

Claude 3 Haiku: 36.1 (#232), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 HaikuDeepSeek Coder 6.7B
LMArena Longer Query1191—

Writing & Preference Not comparable

Claude 3 Haiku: 29.8 (#286), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 HaikuDeepSeek Coder 6.7B
LMArena Text1195—
LMArena Creative Writing1157—
EQ-Bench Creative Writing717—
LMArena Multi-Turn1190—

Frequently asked questions

Is Claude 3 Haiku better than DeepSeek Coder 6.7B?

Claude 3 Haiku has enough public results to be ranked (#333); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

Is Claude 3 Haiku or DeepSeek Coder 6.7B better for coding?

DeepSeek Coder 6.7B scores higher on coding benchmarks: 35.2 versus 26.1 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and DeepSeek Coder 6.7B share?

7 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and DeepSeek Coder 6.7B has 9.

Related comparisons

Go deeper