Noometry

Model comparison

DeepSeek V4 Flash vs GPT-4.1

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 35.9 on the Noometry Index.

Last verified . 32 shared benchmarks.

DeepSeek V4 Flash DeepSeek

53.6

Rank #35 Confirmed

GPT-4.1 OpenAI

35.9

Rank #219 Confirmed

Summary

  • They share 32 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and GPT-4.1 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 11.7.
  • The biggest single-benchmark swing is ARC-AGI-1: 89% for DeepSeek V4 Flash and 5.5% for GPT-4.1.
  • DeepSeek V4 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $8 for GPT-4.1.
  • GPT-4.1 accepts more context: 1.05M tokens versus 1M.
  • DeepSeek V4 Flash has downloadable open weights; the other is API-only.

Side by side

DeepSeek V4 FlashGPT-4.1
ProviderDeepSeekOpenAI
Noometry Index53.635.9
Released2026-04-242025-04-14
WeightsOpenProprietary
Context window1M1.05M
Max output393K33K
Input $ / M tokens$0.15$2
Output $ / M tokens$0.60$8
Results tracked4152

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

Category by category

Coding DeepSeek V4 Flash leads

DeepSeek V4 Flash: 47.9 (#59), GPT-4.1: 34.4 (#238)

BenchmarkDeepSeek V4 FlashGPT-4.1
WeirdML63%39%
LMArena Coding14571391
ALE-Bench1,306558.1
SWE-bench Verified—48.5%
FrontierCode18.8%—
SWE-bench Verified (bash only)—39.6%
Aider Polyglot—52.4%
LMArena WebDev1582—
SciCode49.9%—
CadEval—42%

Agentic & Tool Use Not comparable

DeepSeek V4 Flash: —, GPT-4.1: 34.7 (#43)

BenchmarkDeepSeek V4 FlashGPT-4.1
Berkeley Function Calling Leaderboard—54%

Reasoning DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.7 (#30), GPT-4.1: 11.7 (#339)

BenchmarkDeepSeek V4 FlashGPT-4.1
ARC-AGI-261.4%0.4%
SimpleBench61.1%27%
Kagi LLM Benchmark52.2%52.3%
ARC-AGI-189%5.5%
Chess Puzzles33%6%
LMArena Hard Prompts14441384
DTBench90.9%68.3%
LMCA41.7%25.6%
Epoch Capabilities Index154.49136.78
NYT Connections (extended)89.6%—
CritPt16.6%—
EnigmaEval—2.2%
Mystery Game Puzzles34%—
ForecastBench—61.5

Math DeepSeek V4 Flash leads

DeepSeek V4 Flash: 60.3 (#37), GPT-4.1: 22.3 (#280)

BenchmarkDeepSeek V4 FlashGPT-4.1
FrontierMath (Tiers 1-3)57.5%6%
OTIS Mock AIME 2024-202594.4%38.3%
LMArena Math14271370
FrontierMath Tier 424.4%—
MathArena Final-Answer Competitions76.5%—
ProofBench56%—
Omni-MATH—47.1%
MATH Level 5—83%
FrontierMath (Feb 2025 set)—5.5%
FrontierMath Tier 4 (v1)—0%

Knowledge DeepSeek V4 Flash leads

DeepSeek V4 Flash: 55.4 (#48), GPT-4.1: 37.1 (#160)

BenchmarkDeepSeek V4 FlashGPT-4.1
GPQA Diamond91%66.9%
SimpleQA Verified33.6%31.1%
LMArena Expert14411364
Humanity's Last Exam—5.4%
MMLU-Pro—81.1%
Vectara Hallucination Rate—5.6%
GPQA (HELM)—65.9%

Multimodal Not comparable

DeepSeek V4 Flash: —, GPT-4.1: 38.2 (#67)

BenchmarkDeepSeek V4 FlashGPT-4.1
LMArena Vision—1211
GeoBench—72%

Multilingual DeepSeek V4 Flash leads

DeepSeek V4 Flash: 53.0 (#72), GPT-4.1: 49.4 (#133)

BenchmarkDeepSeek V4 FlashGPT-4.1
LMArena Non-English14201370
LMArena Chinese14681382
LMArena French14391382
LMArena German14181381
LMArena Japanese14061319
LMArena Korean13841339
LMArena Russian14281377
LMArena Spanish14361376

Instruction Following DeepSeek V4 Flash leads

DeepSeek V4 Flash: 74.9 (#81), GPT-4.1: 71.3 (#153)

BenchmarkDeepSeek V4 FlashGPT-4.1
LMArena Instruction Following14211367
IFEval—83.8%

Long Context DeepSeek V4 Flash leads

DeepSeek V4 Flash: 43.8 (#85), GPT-4.1: 40.0 (#163)

BenchmarkDeepSeek V4 FlashGPT-4.1
LMArena Longer Query14341385
Fiction.LiveBench—63.9%

Writing & Preference DeepSeek V4 Flash leads

DeepSeek V4 Flash: 63.8 (#61), GPT-4.1: 57.6 (#125)

BenchmarkDeepSeek V4 FlashGPT-4.1
LMArena Text14321383
LMArena Creative Writing14031363
EQ-Bench Creative Writing15591420
LMArena Multi-Turn14491398
WildBench—85.4%

Frequently asked questions

Is DeepSeek V4 Flash better than GPT-4.1?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 35.9 on the Noometry Index.

Which is cheaper, DeepSeek V4 Flash or GPT-4.1?

DeepSeek V4 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-4.1 lists at $2 and $8.

Is DeepSeek V4 Flash or GPT-4.1 better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 34.4 in the Noometry coding category.

Which has the bigger context window?

GPT-4.1 does, with 1.05M tokens against 1M.

How many benchmarks do DeepSeek V4 Flash and GPT-4.1 share?

32 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and GPT-4.1 has 52.

Related comparisons

Go deeper