Noometry

Model comparison

Claude Opus 4 vs DeepSeek V4.1 Flash

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 43.1 on the Noometry Index.

Last verified . 25 shared benchmarks.

Claude Opus 4 Anthropic

43.1

Rank #100 Confirmed

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Claude Opus 4 scores higher in 1 category and DeepSeek V4.1 Flash in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 42.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 64.4% for Claude Opus 4 and 98.3% for DeepSeek V4.1 Flash.
  • DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $15 / $75 for Claude Opus 4.
  • DeepSeek V4.1 Flash accepts more context: 1M tokens versus 200K.
  • DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4DeepSeek V4.1 Flash
ProviderAnthropicDeepSeek
Noometry Index43.152.8
Released2025-05-222026-09-09
WeightsProprietaryOpen
Context window200K1M
Max output32K393K
Input $ / M tokens$15$0.15
Output $ / M tokens$75$0.60
Results tracked5637

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

Category by category

Coding DeepSeek V4.1 Flash leads

Claude Opus 4: 47.2 (#62), DeepSeek V4.1 Flash: 52.9 (#32)

BenchmarkClaude Opus 4DeepSeek V4.1 Flash
LMArena Coding14421506
SWE-bench Verified70.7%—
SWE-bench Verified (bash only)67.6%—
Aider Polyglot72%—
LMArena WebDev—1619
SciCode—51.9%
GSO6.9%—
WeirdML43.7%—
ALE-Bench—1,092
AlgoTune1.33—

Agentic & Tool Use Claude Opus 4 leads

Claude Opus 4: 34.8 (#42), DeepSeek V4.1 Flash: 31.2 (#69)

BenchmarkClaude Opus 4DeepSeek V4.1 Flash
APEX-Agents—39.5%
Cybench38%—
DeepResearch Bench46.8%—
GDP.pdf—19.8%
LMArena Search1127—
METR Time Horizons63.9%—

Reasoning DeepSeek V4.1 Flash leads

Claude Opus 4: 27.3 (#121), DeepSeek V4.1 Flash: 50.2 (#36)

BenchmarkClaude Opus 4DeepSeek V4.1 Flash
CritPt0.3%14.3%
LMArena Hard Prompts13991483
DTBench81.6%89.9%
LMCA37.4%47%
Epoch Capabilities Index142.67154.9
ARC-AGI-28.6%—
SimpleBench58.8%—
Kagi LLM Benchmark74.3%—
NYT Connections (extended)—89.6%
ARC-AGI-135.7%—
EnigmaEval5.6%—
Mystery Game Puzzles—43%
Surface Evolver Bench—46.3%
ForecastBench61.1—

Math DeepSeek V4.1 Flash leads

Claude Opus 4: 42.0 (#86), DeepSeek V4.1 Flash: 66.7 (#25)

BenchmarkClaude Opus 4DeepSeek V4.1 Flash
OTIS Mock AIME 2024-202564.4%98.3%
LMArena Math13901477
FrontierMath (Tiers 1-3)—67.4%
FrontierMath Tier 4—26.8%
ProofBench—54%
Omni-MATH61.6%—
MATH Level 585%—
FrontierMath (Feb 2025 set)4.5%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge DeepSeek V4.1 Flash leads

Claude Opus 4: 44.0 (#88), DeepSeek V4.1 Flash: 57.9 (#38)

BenchmarkClaude Opus 4DeepSeek V4.1 Flash
GPQA Diamond76.3%89.8%
LMArena Expert13861506
Humanity's Last Exam10.7%—
MMLU-Pro87.5%—
Confabulations15.9%—
Vectara Hallucination Rate12%—
GPQA (HELM)70.8%—

Multimodal DeepSeek V4.1 Flash leads

Claude Opus 4: 31.5 (#106), DeepSeek V4.1 Flash: 39.1 (#61)

BenchmarkClaude Opus 4DeepSeek V4.1 Flash
LMArena Vision11921277
GeoBench49%—
VPCT38%—
Furniture Assembly—34.2%

Multilingual DeepSeek V4.1 Flash leads

Claude Opus 4: 48.8 (#138), DeepSeek V4.1 Flash: 55.0 (#35)

BenchmarkClaude Opus 4DeepSeek V4.1 Flash
LMArena Non-English13621448
LMArena Chinese13861497
LMArena French13721452
LMArena German13911484
LMArena Japanese13311412
LMArena Korean13211452
LMArena Russian13921471
LMArena Spanish13891459

Instruction Following Too close to call

Claude Opus 4: 77.1 (#28), DeepSeek V4.1 Flash: 77.3 (#26)

BenchmarkClaude Opus 4DeepSeek V4.1 Flash
LMArena Instruction Following14061474
IFEval91.8%—

Long Context DeepSeek V4.1 Flash leads

Claude Opus 4: 39.6 (#172), DeepSeek V4.1 Flash: 45.2 (#47)

BenchmarkClaude Opus 4DeepSeek V4.1 Flash
LMArena Longer Query14221475
Fiction.LiveBench61.1%—

Writing & Preference DeepSeek V4.1 Flash leads

Claude Opus 4: 61.2 (#89), DeepSeek V4.1 Flash: 65.4 (#48)

BenchmarkClaude Opus 4DeepSeek V4.1 Flash
LMArena Text13771462
LMArena Creative Writing13871435
EQ-Bench Creative Writing15801540
LMArena Multi-Turn13961457
Short-Story Creative Writing83.6%—
WildBench85.2%—

Frequently asked questions

Is Claude Opus 4 better than DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 43.1 on the Noometry Index.

Which is cheaper, Claude Opus 4 or DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Claude Opus 4 lists at $15 and $75.

Is Claude Opus 4 or DeepSeek V4.1 Flash better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 47.2 in the Noometry coding category.

Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 200K.

How many benchmarks do Claude Opus 4 and DeepSeek V4.1 Flash share?

25 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and DeepSeek V4.1 Flash has 37.

Related comparisons

Go deeper