Noometry

Model comparison

Claude 3 Opus vs DeepSeek-V3.1

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 29.5 on the Noometry Index.

Last verified . 23 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

DeepSeek-V3.1 DeepSeek

42.8

Rank #108 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Claude 3 Opus scores higher in 1 category and DeepSeek-V3.1 in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek-V3.1 leads 38.9 to 14.8.
  • The biggest single-benchmark swing is DTBench: 61.6% for Claude 3 Opus and 82.7% for DeepSeek-V3.1.
  • DeepSeek-V3.1 has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusDeepSeek-V3.1
ProviderAnthropicDeepSeek
Noometry Index29.542.8
Released2024-02-292025-08-21
WeightsProprietaryOpen
Context window—164K
Max output—8K
Input $ / M tokens—$0.25
Output $ / M tokens—$0.95
Results tracked4627

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

Category by category

Coding DeepSeek-V3.1 leads

Claude 3 Opus: 32.9 (#267), DeepSeek-V3.1: 40.3 (#144)

BenchmarkClaude 3 OpusDeepSeek-V3.1
WeirdML19.2%38.4%
LMArena Coding12641417
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
BigCodeBench Complete57.4%—
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

Claude 3 Opus: 24.6 (#116), DeepSeek-V3.1: —

BenchmarkClaude 3 OpusDeepSeek-V3.1
Cybench10%—
METR Time Horizons29.5%—

Reasoning DeepSeek-V3.1 leads

Claude 3 Opus: 14.6 (#324), DeepSeek-V3.1: 27.9 (#110)

BenchmarkClaude 3 OpusDeepSeek-V3.1
SimpleBench23.5%40%
LMArena Hard Prompts12451417
DTBench61.6%82.7%
LMCA17%24.3%
Epoch Capabilities Index126.91139.92
ForecastBench58.458
Kagi LLM Benchmark—53.2%
Chess Puzzles5%—
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
LiveBench Data Analysis57.9%—
LiveBench49.2%—
WinoGrande88.5%—

Math DeepSeek-V3.1 leads

Claude 3 Opus: 14.8 (#299), DeepSeek-V3.1: 38.9 (#122)

BenchmarkClaude 3 OpusDeepSeek-V3.1
LMArena Math12731420
OTIS Mock AIME 2024-20254.7%—
LiveBench Math43.6%—
MATH Level 537.5%—

Knowledge DeepSeek-V3.1 leads

Claude 3 Opus: 24.5 (#267), DeepSeek-V3.1: 43.7 (#90)

BenchmarkClaude 3 OpusDeepSeek-V3.1
LMArena Expert12231405
GPQA Diamond47.2%—
SimpleQA Verified12.6%—
Confabulations22.7%—
Vectara Hallucination Rate—5.5%
MMLU84.6%—

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), DeepSeek-V3.1: —

BenchmarkClaude 3 OpusDeepSeek-V3.1
LMArena Vision1023—

Multilingual DeepSeek-V3.1 leads

Claude 3 Opus: 41.4 (#207), DeepSeek-V3.1: 51.6 (#106)

BenchmarkClaude 3 OpusDeepSeek-V3.1
LMArena Non-English12581400
LMArena Chinese12481469
LMArena French12751447
LMArena German12581411
LMArena Japanese12041378
LMArena Korean11871337
LMArena Russian12801405
LMArena Spanish12461431

Instruction Following DeepSeek-V3.1 leads

Claude 3 Opus: 64.1 (#228), DeepSeek-V3.1: 73.9 (#110)

BenchmarkClaude 3 OpusDeepSeek-V3.1
LMArena Instruction Following12481400
LiveBench Instruction Following63.9%—

Long Context Claude 3 Opus leads

Claude 3 Opus: 38.2 (#202), DeepSeek-V3.1: 36.3 (#232)

BenchmarkClaude 3 OpusDeepSeek-V3.1
LMArena Longer Query12591422
Fiction.LiveBench—52.8%

Writing & Preference DeepSeek-V3.1 leads

Claude 3 Opus: 47.2 (#213), DeepSeek-V3.1: 60.3 (#98)

BenchmarkClaude 3 OpusDeepSeek-V3.1
LMArena Text12621420
LMArena Creative Writing12351401
LMArena Multi-Turn12751408
EQ-Bench Creative Writing—1436
LiveBench Language50.4%—

Frequently asked questions

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

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 29.5 on the Noometry Index.

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

DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 32.9 in the Noometry coding category.

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

23 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and DeepSeek-V3.1 has 27.

Related comparisons

Go deeper