Noometry

Model comparison

Claude 3 Opus vs Deepseek Coder v2

Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 29.5 on the Noometry Index.

Last verified . 22 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude 3 Opus scores higher in 4 categories and Deepseek Coder v2 in 4 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Deepseek Coder v2 leads 34.9 to 14.8.
  • Deepseek Coder v2 has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusDeepseek Coder v2
ProviderAnthropicDeepSeek
Noometry Index29.535.9
Released2024-02-292024-06-17
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4624

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

Category by category

Coding Deepseek Coder v2 leads

Claude 3 Opus: 32.9 (#267), Deepseek Coder v2: 38.1 (#183)

BenchmarkClaude 3 OpusDeepseek Coder v2
BigCodeBench Instruct45.5%48.2%
LMArena Coding12641251
BigCodeBench Complete57.4%59.7%
HumanEval+77.4%82.3%
MBPP+73.3%75.1%
WeirdML19.2%—
LiveBench Coding38.6%—

Agentic & Tool Use Not comparable

Claude 3 Opus: 24.6 (#116), Deepseek Coder v2: —

BenchmarkClaude 3 OpusDeepseek Coder v2
Cybench10%—
METR Time Horizons29.5%—

Reasoning Deepseek Coder v2 leads

Claude 3 Opus: 14.6 (#324), Deepseek Coder v2: 23.6 (#176)

BenchmarkClaude 3 OpusDeepseek Coder v2
LMArena Hard Prompts12451207
WinoGrande88.5%83.7%
SimpleBench23.5%—
Chess Puzzles5%—
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
DTBench61.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
Epoch Capabilities Index126.91—
ForecastBench58.4—
LiveBench49.2%—

Math Deepseek Coder v2 leads

Claude 3 Opus: 14.8 (#299), Deepseek Coder v2: 34.9 (#190)

BenchmarkClaude 3 OpusDeepseek Coder v2
LMArena Math12731241
OTIS Mock AIME 2024-20254.7%—
LiveBench Math43.6%—
MATH Level 537.5%—
GSM8K—94.5%

Knowledge Deepseek Coder v2 leads

Claude 3 Opus: 24.5 (#267), Deepseek Coder v2: 32.3 (#212)

BenchmarkClaude 3 OpusDeepseek Coder v2
LMArena Expert12231181
GPQA Diamond47.2%—
SimpleQA Verified12.6%—
Confabulations22.7%—
ARC (AI2) Challenge—64.3%
MMLU84.6%—

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), Deepseek Coder v2: —

BenchmarkClaude 3 OpusDeepseek Coder v2
LMArena Vision1023—

Multilingual Claude 3 Opus leads

Claude 3 Opus: 41.4 (#207), Deepseek Coder v2: 36.3 (#240)

BenchmarkClaude 3 OpusDeepseek Coder v2
LMArena Non-English12581182
LMArena Chinese12481201
LMArena French12751185
LMArena German12581164
LMArena Japanese12041126
LMArena Korean11871104
LMArena Russian12801188
LMArena Spanish12461153

Instruction Following Claude 3 Opus leads

Claude 3 Opus: 64.1 (#228), Deepseek Coder v2: 61.7 (#242)

BenchmarkClaude 3 OpusDeepseek Coder v2
LMArena Instruction Following12481180
LiveBench Instruction Following63.9%—

Long Context Claude 3 Opus leads

Claude 3 Opus: 38.2 (#202), Deepseek Coder v2: 37.0 (#224)

BenchmarkClaude 3 OpusDeepseek Coder v2
LMArena Longer Query12591219

Writing & Preference Claude 3 Opus leads

Claude 3 Opus: 47.2 (#213), Deepseek Coder v2: 38.2 (#253)

BenchmarkClaude 3 OpusDeepseek Coder v2
LMArena Text12621191
LMArena Creative Writing12351120
LMArena Multi-Turn12751177
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than Deepseek Coder v2?

Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 29.5 on the Noometry Index.

Is Claude 3 Opus or Deepseek Coder v2 better for coding?

Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3 Opus and Deepseek Coder v2 share?

22 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Deepseek Coder v2 has 24.

Related comparisons

Go deeper