Noometry

Model comparison

Claude Opus 4.1 vs DeepSeek-V3

Claude Opus 4.1 is the stronger model overall, scoring 41.0 to 39.5 on the Noometry Index. DeepSeek-V3 costs 74× less per token, which makes it the better buy when Claude Opus 4.1's lead doesn't matter for your workload.

Last verified . 30 shared benchmarks.

Claude Opus 4.1 Anthropic

41.0

Rank #142 Confirmed

DeepSeek-V3 DeepSeek

39.5

Rank #166 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Claude Opus 4.1 scores higher in 7 categories and DeepSeek-V3 in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.1 leads 32.2 to 20.5.
  • The biggest single-benchmark swing is SimpleBench: 60% for Claude Opus 4.1 and 27.2% for DeepSeek-V3.
  • DeepSeek-V3 is cheaper at $0.24 / $0.90 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
  • Claude Opus 4.1 accepts more context: 200K tokens versus 164K.
  • DeepSeek-V3 has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.1DeepSeek-V3
ProviderAnthropicDeepSeek
Noometry Index41.039.5
Released2025-08-052024-12-26
WeightsProprietaryOpen
Context window200K164K
Max output32K164K
Input $ / M tokens$15$0.24
Output $ / M tokens$75$0.90
Results tracked4860

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

Category by category

Coding Claude Opus 4.1 leads

Claude Opus 4.1: 44.4 (#73), DeepSeek-V3: 42.3 (#106)

BenchmarkClaude Opus 4.1DeepSeek-V3
WeirdML45.9%36.1%
LMArena Coding14791368
SWE-bench Verified73.3%—
Aider Polyglot—55.1%
LMArena WebDev1390—
SciCode—35.8%
BigCodeBench Instruct—50%
LiveBench Coding—70.9%
BigCodeBench Complete—62.2%
ALE-Bench674.77—
AlgoTune1.34—
HumanEval+—86.6%
MBPP+—73%

Agentic & Tool Use Not comparable

Claude Opus 4.1: 35.0 (#41), DeepSeek-V3: —

BenchmarkClaude Opus 4.1DeepSeek-V3
METR Time Horizons66.8%49.6%
Terminal-Bench38%—
GDPval43.6%—
Cybench42%—
DeepResearch Bench48.3%—
LMArena Search1148—

Reasoning Claude Opus 4.1 leads

Claude Opus 4.1: 32.2 (#76), DeepSeek-V3: 20.5 (#236)

BenchmarkClaude Opus 4.1DeepSeek-V3
SimpleBench60%27.2%
LMArena Hard Prompts14431365
DTBench80%64.8%
LMCA37.1%15.5%
Epoch Capabilities Index144.12135.94
ForecastBench6259.1
Kagi LLM Benchmark—52.3%
CritPt—0%
Chess Puzzles7%—
EnigmaEval7.2%—
EBR-Bench7.9%—
LiveBench Reasoning—65.8%
Mystery Game Puzzles21%—
LiveBench Data Analysis—60.9%
BIG-Bench Hard—87.5%
HellaSwag—88.9%
LiveBench—66.9%
PIQA—84.7%
WinoGrande—85.2%

Math DeepSeek-V3 leads

Claude Opus 4.1: 22.3 (#277), DeepSeek-V3: 32.1 (#219)

BenchmarkClaude Opus 4.1DeepSeek-V3
OTIS Mock AIME 2024-202568.9%37.8%
LMArena Math14311373
FrontierMath (Feb 2025 set)7.2%1.7%
FrontierMath (Tiers 1-3)12.6%—
FrontierMath Tier 42.4%—
Omni-MATH—40.3%
LiveBench Math—73.5%
MATH Level 5—75.5%
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Opus 4.1 leads

Claude Opus 4.1: 42.0 (#101), DeepSeek-V3: 37.5 (#155)

BenchmarkClaude Opus 4.1DeepSeek-V3
GPQA Diamond77.3%67.6%
Confabulations17.1%26.1%
Vectara Hallucination Rate11.8%6.1%
LMArena Expert14391351
Humanity's Last Exam11.5%—
MMLU-Pro—72.3%
GPQA (HELM)—53.8%
ARC (AI2) Challenge—95.3%
MMLU—87.2%
TriviaQA—82.9%

Multimodal Not comparable

Claude Opus 4.1: 26.8 (#119), DeepSeek-V3: —

BenchmarkClaude Opus 4.1DeepSeek-V3
VPCT35%—

Multilingual Claude Opus 4.1 leads

Claude Opus 4.1: 52.0 (#95), DeepSeek-V3: 48.5 (#143)

BenchmarkClaude Opus 4.1DeepSeek-V3
LMArena Non-English14051358
LMArena Chinese14271391
LMArena French14311385
LMArena German14131374
LMArena Japanese13781333
LMArena Korean13801319
LMArena Russian14221373
LMArena Spanish14481358

Instruction Following Claude Opus 4.1 leads

Claude Opus 4.1: 75.6 (#58), DeepSeek-V3: 72.8 (#130)

BenchmarkClaude Opus 4.1DeepSeek-V3
LMArena Instruction Following14351345
LiveBench Instruction Following—81.5%
IFEval—83.2%

Long Context Claude Opus 4.1 leads

Claude Opus 4.1: 44.5 (#63), DeepSeek-V3: 34.0 (#253)

BenchmarkClaude Opus 4.1DeepSeek-V3
LMArena Longer Query14551352
Fiction.LiveBench—50%

Writing & Preference Claude Opus 4.1 leads

Claude Opus 4.1: 62.4 (#74), DeepSeek-V3: 57.4 (#130)

BenchmarkClaude Opus 4.1DeepSeek-V3
LMArena Text14191375
LMArena Creative Writing14121364
Short-Story Creative Writing84.7%77%
LMArena Multi-Turn14441389
EQ-Bench Creative Writing—1472
WildBench—83%
LiveBench Language—49.1%

Frequently asked questions

Is Claude Opus 4.1 better than DeepSeek-V3?

Claude Opus 4.1 is the stronger model overall, scoring 41.0 to 39.5 on the Noometry Index. DeepSeek-V3 costs 74× less per token, which makes it the better buy when Claude Opus 4.1's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.1 or DeepSeek-V3?

DeepSeek-V3 is cheaper. It lists at $0.24 per million input tokens and $0.90 per million output tokens; Claude Opus 4.1 lists at $15 and $75.

Is Claude Opus 4.1 or DeepSeek-V3 better for coding?

Claude Opus 4.1 scores higher on coding benchmarks: 44.4 versus 42.3 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.1 does, with 200K tokens against 164K.

How many benchmarks do Claude Opus 4.1 and DeepSeek-V3 share?

30 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and DeepSeek-V3 has 60.

Related comparisons

Go deeper