Noometry

Model comparison

Claude 3 Sonnet vs DeepSeek Coder 6.7B

Claude 3 Sonnet has enough public results to be ranked (#319); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

Last verified . 7 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

DeepSeek Coder 6.7B DeepSeek

37.6

Unranked Sparse

Summary

  • They share 7 benchmarks with published results for both. Claude 3 Sonnet 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 35.8 to 29.6.
  • The biggest single-benchmark swing is BigCodeBench Complete: 53.8% for Claude 3 Sonnet 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 SonnetDeepSeek Coder 6.7B
ProviderAnthropicDeepSeek
Noometry Index29.037.6
Released2024-02-292023-11-02
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked309

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

Category by category

Coding DeepSeek Coder 6.7B leads

Claude 3 Sonnet: 29.6 (#302), DeepSeek Coder 6.7B: 35.8 (#219)

BenchmarkClaude 3 SonnetDeepSeek Coder 6.7B
BigCodeBench Instruct42.7%35.5%
BigCodeBench Complete53.8%43.8%
HumanEval+64%71.3%
MBPP+69.3%65.6%
WeirdML10.2%—
LMArena Coding1223—

Reasoning Not comparable

Claude 3 Sonnet: 20.5 (#237), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 SonnetDeepSeek Coder 6.7B
Epoch Capabilities Index120.789.62
WinoGrande75.1%57.6%
LMArena Hard Prompts1197—
DTBench53.6%—

Math Not comparable

Claude 3 Sonnet: 10.7 (#310), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 SonnetDeepSeek Coder 6.7B
OTIS Mock AIME 2024-20252.5%—
LMArena Math1213—
MATH Level 518.2%—
GSM8K—21.3%

Knowledge Not comparable

Claude 3 Sonnet: 21.1 (#276), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 SonnetDeepSeek Coder 6.7B
MMLU75.9%36.4%
GPQA Diamond40.6%—
LMArena Expert1173—
ARC (AI2) Challenge—36.4%

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 SonnetDeepSeek Coder 6.7B
LMArena Vision984—

Multilingual Not comparable

Claude 3 Sonnet: 37.8 (#234), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 SonnetDeepSeek Coder 6.7B
LMArena Non-English1205—
LMArena Chinese1189—
LMArena French1229—
LMArena German1204—
LMArena Japanese1131—
LMArena Korean1128—
LMArena Russian1227—
LMArena Spanish1204—

Instruction Following Not comparable

Claude 3 Sonnet: 62.8 (#235), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 SonnetDeepSeek Coder 6.7B
LMArena Instruction Following1199—

Long Context Not comparable

Claude 3 Sonnet: 36.7 (#228), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 SonnetDeepSeek Coder 6.7B
LMArena Longer Query1211—

Writing & Preference Not comparable

Claude 3 Sonnet: 42.1 (#238), DeepSeek Coder 6.7B: —

BenchmarkClaude 3 SonnetDeepSeek Coder 6.7B
LMArena Text1218—
LMArena Creative Writing1186—
LMArena Multi-Turn1227—

Frequently asked questions

Is Claude 3 Sonnet better than DeepSeek Coder 6.7B?

Claude 3 Sonnet has enough public results to be ranked (#319); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

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

DeepSeek Coder 6.7B scores higher on coding benchmarks: 35.8 versus 29.6 in the Noometry coding category.

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

7 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and DeepSeek Coder 6.7B has 9.

Related comparisons

Go deeper