Noometry

Model comparison

Claude Opus 4.1 vs DeepSeek-V3.1

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 40.8 on the Noometry Index.

Last verified . 24 shared benchmarks.

Claude Opus 4.1 Anthropic

40.8

Rank #136 Confirmed

DeepSeek-V3.1 DeepSeek

42.2

Rank #106 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude Opus 4.1 scores higher in 6 categories and DeepSeek-V3.1 in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek-V3.1 leads 36.1 to 22.0.
  • The biggest single-benchmark swing is SimpleBench: 60% for Claude Opus 4.1 and 40% for DeepSeek-V3.1.
  • DeepSeek-V3.1 is cheaper at $0.25 / $0.95 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-V3.1 has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.1DeepSeek-V3.1
ProviderAnthropicDeepSeek
Noometry Index40.842.2
Released2025-08-052025-08-21
WeightsProprietaryOpen
Context window200K164K
Max output32K8K
Input $ / M tokens$15$0.25
Output $ / M tokens$75$0.95
Results tracked4827

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: 44.3 (#69), DeepSeek-V3.1: 39.8 (#140)

BenchmarkClaude Opus 4.1DeepSeek-V3.1
WeirdML45.9%38.4%
LMArena Coding14791417
SWE-bench Verified73.3%—
LMArena WebDev1390—
ALE-Bench674.77—
AlgoTune1.34—

Agentic & Tool Use Not comparable

Claude Opus 4.1: 34.8 (#38), DeepSeek-V3.1: —

BenchmarkClaude Opus 4.1DeepSeek-V3.1
Terminal-Bench38%—
GDPval43.6%—
Cybench42%—
DeepResearch Bench48.3%—
LMArena Search1148—
METR Time Horizons66.8%—

Reasoning Claude Opus 4.1 leads

Claude Opus 4.1: 31.6 (#70), DeepSeek-V3.1: 27.3 (#109)

BenchmarkClaude Opus 4.1DeepSeek-V3.1
SimpleBench60%40%
LMArena Hard Prompts14431417
DTBench80%82.7%
LMCA37.1%24.3%
Epoch Capabilities Index144.11139.92
ForecastBench6258
Kagi LLM Benchmark—53.2%
Chess Puzzles7%—
EnigmaEval7.2%—
EBR-Bench7.9%—
Mystery Game Puzzles21%—

Math DeepSeek-V3.1 leads

Claude Opus 4.1: 22.0 (#267), DeepSeek-V3.1: 36.1 (#125)

BenchmarkClaude Opus 4.1DeepSeek-V3.1
LMArena Math14301420
FrontierMath (Tiers 1-3)12.6%—
FrontierMath Tier 42.4%—
OTIS Mock AIME 2024-202568.9%—
FrontierMath (Feb 2025 set)7.2%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge DeepSeek-V3.1 leads

Claude Opus 4.1: 41.9 (#93), DeepSeek-V3.1: 43.0 (#86)

BenchmarkClaude Opus 4.1DeepSeek-V3.1
Vectara Hallucination Rate11.8%5.5%
LMArena Expert14391403
GPQA Diamond77.3%—
Humanity's Last Exam11.5%—
Confabulations17.1%—

Multimodal Not comparable

Claude Opus 4.1: 26.2 (#114), DeepSeek-V3.1: —

BenchmarkClaude Opus 4.1DeepSeek-V3.1
VPCT35%—

Multilingual Too close to call

Claude Opus 4.1: 52.1 (#90), DeepSeek-V3.1: 51.8 (#100)

BenchmarkClaude Opus 4.1DeepSeek-V3.1
LMArena Non-English14051400
LMArena Chinese14271470
LMArena French14321447
LMArena German14121412
LMArena Japanese13781374
LMArena Korean13811337
LMArena Russian14211405
LMArena Spanish14481429

Instruction Following Claude Opus 4.1 leads

Claude Opus 4.1: 75.8 (#53), DeepSeek-V3.1: 74.1 (#105)

BenchmarkClaude Opus 4.1DeepSeek-V3.1
LMArena Instruction Following14361400

Long Context Claude Opus 4.1 leads

Claude Opus 4.1: 44.5 (#60), DeepSeek-V3.1: 36.3 (#227)

BenchmarkClaude Opus 4.1DeepSeek-V3.1
LMArena Longer Query14551422
Fiction.LiveBench—52.8%

Writing & Preference Claude Opus 4.1 leads

Claude Opus 4.1: 62.6 (#70), DeepSeek-V3.1: 60.5 (#93)

BenchmarkClaude Opus 4.1DeepSeek-V3.1
LMArena Text14191420
LMArena Creative Writing14121401
LMArena Multi-Turn14441408
Short-Story Creative Writing84.7%—
EQ-Bench Creative Writing—1436

Frequently asked questions

Is Claude Opus 4.1 better than DeepSeek-V3.1?

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 40.8 on the Noometry Index.

Which is cheaper, Claude Opus 4.1 or DeepSeek-V3.1?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Claude Opus 4.1 lists at $15 and $75.

Is Claude Opus 4.1 or DeepSeek-V3.1 better for coding?

Claude Opus 4.1 scores higher on coding benchmarks: 44.3 versus 39.8 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-V3.1 share?

24 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and DeepSeek-V3.1 has 27.

Related comparisons

Go deeper