Noometry

Model comparison

DeepSeek V4.1 Flash vs GPT-4

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 29.1 on the Noometry Index.

Last verified . 24 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

52.8

Rank #38 Confirmed

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Summary

  • They share 24 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and GPT-4 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 10.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for DeepSeek V4.1 Flash and 1.1% for GPT-4.
  • DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $30 / $60 for GPT-4.
  • DeepSeek V4.1 Flash accepts more context: 1M tokens versus 8K.
  • DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4.1 FlashGPT-4
ProviderDeepSeekOpenAI
Noometry Index52.829.1
Released2026-09-092023-03-14
WeightsOpenProprietary
Context window1M8K
Max output393K8K
Input $ / M tokens$0.15$30
Output $ / M tokens$0.60$60
Results tracked3738

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-4: 31.6 (#283)

BenchmarkDeepSeek V4.1 FlashGPT-4
LMArena Coding15061254
LMArena WebDev1619—
SciCode51.9%—
WeirdML—12.4%
BigCodeBench Instruct—46%
BigCodeBench Complete—57.2%
ALE-Bench1,092—
HumanEval+—79.3%

Agentic & Tool Use Not comparable

DeepSeek V4.1 Flash: 31.2 (#69), GPT-4: —

BenchmarkDeepSeek V4.1 FlashGPT-4
APEX-Agents39.5%—
GDP.pdf19.8%—
METR Time Horizons—36.1%

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 50.2 (#36), GPT-4: 17.8 (#289)

BenchmarkDeepSeek V4.1 FlashGPT-4
LMArena Hard Prompts14831241
Mystery Game Puzzles43%12%
DTBench89.9%62.7%
LMCA47%17.1%
Epoch Capabilities Index154.9125.89
NYT Connections (extended)89.6%—
CritPt14.3%—
Chess Puzzles—4%
Surface Evolver Bench46.3%—
BIG-Bench Hard—75.1%
ForecastBench—57.8
HellaSwag—95.3%
WinoGrande—87.5%

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 66.7 (#25), GPT-4: 10.8 (#309)

BenchmarkDeepSeek V4.1 FlashGPT-4
OTIS Mock AIME 2024-202598.3%1.1%
LMArena Math14771269
FrontierMath (Tiers 1-3)67.4%—
FrontierMath Tier 426.8%—
ProofBench54%—
MATH Level 5—23%
GSM8K—92%

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 57.9 (#38), GPT-4: 18.4 (#282)

BenchmarkDeepSeek V4.1 FlashGPT-4
GPQA Diamond89.8%35.7%
LMArena Expert15061211
MMLU—86.4%
TriviaQA—84.8%

Multimodal Not comparable

DeepSeek V4.1 Flash: 39.1 (#61), GPT-4: —

BenchmarkDeepSeek V4.1 FlashGPT-4
LMArena Vision1277—
Furniture Assembly34.2%—

Multilingual DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 55.0 (#35), GPT-4: 40.6 (#215)

BenchmarkDeepSeek V4.1 FlashGPT-4
LMArena Non-English14481246
LMArena Chinese14971242
LMArena French14521283
LMArena German14841251
LMArena Japanese14121209
LMArena Korean14521184
LMArena Russian14711251
LMArena Spanish14591261

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.3 (#26), GPT-4: 65.3 (#222)

BenchmarkDeepSeek V4.1 FlashGPT-4
LMArena Instruction Following14741241

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#47), GPT-4: 37.7 (#212)

BenchmarkDeepSeek V4.1 FlashGPT-4
LMArena Longer Query14751244

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.4 (#48), GPT-4: 34.9 (#268)

BenchmarkDeepSeek V4.1 FlashGPT-4
LMArena Text14621263
LMArena Creative Writing14351244
EQ-Bench Creative Writing1540752
LMArena Multi-Turn14571257

Frequently asked questions

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

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 29.1 on the Noometry Index.

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

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-4 lists at $30 and $60.

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

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 8K.

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

24 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and GPT-4 has 38.

Related comparisons

Go deeper