Noometry

Model comparison

DeepSeek V4.1 Flash vs GPT-4 Turbo

DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 30.3 on the Noometry Index.

Last verified . 17 shared benchmarks.

DeepSeek V4.1 Flash DeepSeek

50.3

Rank #40 Confirmed

GPT-4 Turbo OpenAI

30.3

Rank #281 Confirmed

Summary

  • They share 17 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and GPT-4 Turbo in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek V4.1 Flash leads 48.4 to 8.6.
  • The biggest single-benchmark swing is LMCA: 47% for DeepSeek V4.1 Flash and 9.8% for GPT-4 Turbo.
  • DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • 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-4 Turbo
ProviderDeepSeekOpenAI
Noometry Index50.330.3
Released2026-09-092023-11-06
WeightsOpenProprietary
Context window1M128K
Max output393K4K
Input $ / M tokens$0.15$10
Output $ / M tokens$0.60$30
Results tracked2536

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: 52.8 (#29), GPT-4 Turbo: 33.4 (#247)

BenchmarkDeepSeek V4.1 FlashGPT-4 Turbo
LMArena Coding15111268
LMArena WebDev1620—
SciCode51.9%—
WeirdML—18%
BigCodeBench Instruct—48.2%
BigCodeBench Complete—58.2%
ALE-Bench1,092—
HumanEval+—86.6%
MBPP+—73.3%

Agentic & Tool Use Not comparable

DeepSeek V4.1 Flash: —, GPT-4 Turbo: —

BenchmarkDeepSeek V4.1 FlashGPT-4 Turbo
METR Time Horizons—36.7%

Reasoning DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 46.2 (#39), GPT-4 Turbo: 14.9 (#311)

BenchmarkDeepSeek V4.1 FlashGPT-4 Turbo
LMArena Hard Prompts14851251
DTBench89.9%61.6%
LMCA47%9.8%
Epoch Capabilities Index155.01127.25
SimpleBench—25.1%
NYT Connections (extended)89.6%—
CritPt14.3%—
Chess Puzzles—6%
Surface Evolver Bench46.3%—
ForecastBench—59.4

Math DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 48.4 (#52), GPT-4 Turbo: 8.6 (#316)

BenchmarkDeepSeek V4.1 FlashGPT-4 Turbo
LMArena Math14931272
FrontierMath (Tiers 1-3)—0.7%
OTIS Mock AIME 2024-2025—6.7%
ProofBench54%—
MATH Level 5—46.7%

Knowledge DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 41.6 (#97), GPT-4 Turbo: 24.3 (#263)

BenchmarkDeepSeek V4.1 FlashGPT-4 Turbo
LMArena Expert15051223
GPQA Diamond—46.6%
Confabulations—28.4%
MMLU—81.3%

Multimodal Not comparable

DeepSeek V4.1 Flash: —, GPT-4 Turbo: 30.0 (#104)

BenchmarkDeepSeek V4.1 FlashGPT-4 Turbo
LMArena Vision—1090

Multilingual DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 55.5 (#29), GPT-4 Turbo: 40.7 (#211)

BenchmarkDeepSeek V4.1 FlashGPT-4 Turbo
LMArena Non-English14521245
LMArena Chinese15061242
LMArena French14481275
LMArena Russian14731259
LMArena Spanish14991260
LMArena German—1259
LMArena Japanese—1194
LMArena Korean—1187

Instruction Following DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 77.6 (#24), GPT-4 Turbo: 66.0 (#211)

BenchmarkDeepSeek V4.1 FlashGPT-4 Turbo
LMArena Instruction Following14751250

Long Context DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 45.2 (#46), GPT-4 Turbo: 38.0 (#200)

BenchmarkDeepSeek V4.1 FlashGPT-4 Turbo
LMArena Longer Query14761254

Writing & Preference DeepSeek V4.1 Flash leads

DeepSeek V4.1 Flash: 65.8 (#43), GPT-4 Turbo: 47.9 (#201)

BenchmarkDeepSeek V4.1 FlashGPT-4 Turbo
LMArena Text14651272
LMArena Creative Writing14361269
LMArena Multi-Turn14601267
EQ-Bench Creative Writing1540—

Frequently asked questions

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

DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 30.3 on the Noometry Index.

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

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-4 Turbo lists at $10 and $30.

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

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.8 versus 33.4 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-4 Turbo share?

17 benchmarks have published results for both models. DeepSeek V4.1 Flash has 25 scored results on Noometry and GPT-4 Turbo has 36.

Related comparisons

Go deeper