Noometry

Model comparison

DeepSeek V4.1 Flash vs GPT-4o

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 28.6 on the Noometry Index.

Last verified . 25 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

GPT-4o OpenAI

28.6

Rank #324 Confirmed

Summary

  • They share 25 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 10 categories and GPT-4o in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 10.6.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for DeepSeek V4.1 Flash and 6.4% for GPT-4o.
  • DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $2.50 / $10 for GPT-4o.
  • DeepSeek V4.1 Flash accepts more context: 1M tokens versus 128K.
  • DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4.1 FlashGPT-4o
ProviderDeepSeekOpenAI
Noometry Index52.828.6
Released2026-09-092024-05-13
WeightsOpenProprietary
Context window1M128K
Max output393K16K
Input $ / M tokens$0.15$2.50
Output $ / M tokens$0.60$10
Results tracked3772

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

Category by category

Coding DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 52.9 (#32), GPT-4o: 24.8 (#328)

BenchmarkDeepSeek V4.1 FlashGPT-4o
LMArena Coding15061297
SWE-bench Verified—31%
SWE-bench Verified (bash only)—21.6%
Aider Polyglot—45.3%
LMArena WebDev1619—
SciCode51.9%—
GSO—0%
WeirdML—25.1%
BigCodeBench Instruct—51.1%
LiveBench Coding—51.4%
BigCodeBench Complete—61.1%
CadEval—26%
ALE-Bench1,092—
HumanEval+—87.2%
MBPP+—72.2%

Agentic & Tool Use DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 31.2 (#69), GPT-4o: 21.0 (#141)

BenchmarkDeepSeek V4.1 FlashGPT-4o
APEX-Agents39.5%—
GDPval—9.9%
TheAgentCompany—8.6%
Cybench—12.5%
BALROG—32.3%
GDP.pdf19.8%—
LMArena Search—1006
METR Time Horizons—40.8%

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), GPT-4o: 9.4 (#343)

BenchmarkDeepSeek V4.1 FlashGPT-4o
CritPt14.3%0%
LMArena Hard Prompts14831281
DTBench89.9%64.5%
LMCA47%16.6%
Epoch Capabilities Index154.9128.97
ARC-AGI-2—0%
SimpleBench—17.8%
NYT Connections (extended)89.6%—
ARC-AGI-1—4.5%
Chess Puzzles—13%
EnigmaEval—0.8%
LiveBench Reasoning—55.8%
Mystery Game Puzzles43%—
LiveBench Data Analysis—60.9%
Surface Evolver Bench46.3%—
ForecastBench—57.7
LiveBench—55.3%

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), GPT-4o: 10.6 (#312)

BenchmarkDeepSeek V4.1 FlashGPT-4o
FrontierMath (Tiers 1-3)67.4%0.4%
OTIS Mock AIME 2024-202598.3%6.4%
LMArena Math14771285
FrontierMath Tier 426.8%—
ProofBench54%—
Omni-MATH—29.3%
LiveBench Math—49.5%
MATH Level 5—53.3%
FrontierMath (Feb 2025 set)—0.3%

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), GPT-4o: 28.8 (#242)

BenchmarkDeepSeek V4.1 FlashGPT-4o
GPQA Diamond89.8%49.2%
LMArena Expert15061250
Humanity's Last Exam—2.7%
SimpleQA Verified—26%
MMLU-Pro—71.3%
Confabulations—15.3%
Vectara Hallucination Rate—9.6%
GPQA (HELM)—52%
MMLU—88.1%

Multimodal DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 39.1 (#61), GPT-4o: 34.5 (#91)

BenchmarkDeepSeek V4.1 FlashGPT-4o
LMArena Vision12771137
Video-MME—71.9%
GeoBench—71%
VPCT—40%
Furniture Assembly34.2%—
ScienceQA—88.5%

Multilingual DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 55.0 (#35), GPT-4o: 43.2 (#186)

BenchmarkDeepSeek V4.1 FlashGPT-4o
LMArena Non-English14481283
LMArena Chinese14971277
LMArena French14521304
LMArena German14841282
LMArena Japanese14121257
LMArena Korean14521234
LMArena Russian14711286
LMArena Spanish14591292

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), GPT-4o: 66.6 (#207)

BenchmarkDeepSeek V4.1 FlashGPT-4o
LMArena Instruction Following14741278
LiveBench Instruction Following—68.6%
IFEval—81.7%

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#47), GPT-4o: 39.4 (#179)

BenchmarkDeepSeek V4.1 FlashGPT-4o
LMArena Longer Query14751289
Fiction.LiveBench—66.7%

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.4 (#48), GPT-4o: 52.6 (#166)

BenchmarkDeepSeek V4.1 FlashGPT-4o
LMArena Text14621300
LMArena Creative Writing14351292
LMArena Multi-Turn14571302
Short-Story Creative Writing—81.8%
EQ-Bench Creative Writing1540—
WildBench—82.8%
LiveBench Language—47.6%

Frequently asked questions

Is DeepSeek V4.1 Flash better than GPT-4o?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 28.6 on the Noometry Index.

Which is cheaper, DeepSeek V4.1 Flash or GPT-4o?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-4o lists at $2.50 and $10.

Is DeepSeek V4.1 Flash or GPT-4o better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 24.8 in the Noometry coding category.

Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 128K.

How many benchmarks do DeepSeek V4.1 Flash and GPT-4o share?

25 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and GPT-4o has 72.

Related comparisons

Go deeper