Noometry

Model comparison

DeepSeek-V3.1 vs GPT-4

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 29.1 on the Noometry Index.

Last verified . 23 shared benchmarks.

DeepSeek-V3.1 DeepSeek

42.8

Rank #108 Confirmed

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Summary

  • They share 23 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and GPT-4 in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where DeepSeek-V3.1 leads 38.9 to 10.8.
  • The biggest single-benchmark swing is WeirdML: 38.4% for DeepSeek-V3.1 and 12.4% for GPT-4.
  • DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $30 / $60 for GPT-4.
  • DeepSeek-V3.1 accepts more context: 164K tokens versus 8K.
  • DeepSeek-V3.1 has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V3.1GPT-4
ProviderDeepSeekOpenAI
Noometry Index42.829.1
Released2025-08-212023-03-14
WeightsOpenProprietary
Context window164K8K
Max output8K8K
Input $ / M tokens$0.25$30
Output $ / M tokens$0.95$60
Results tracked2738

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

Category by category

Coding DeepSeek-V3.1 leads

DeepSeek-V3.1: 40.3 (#144), GPT-4: 31.6 (#283)

BenchmarkDeepSeek-V3.1GPT-4
WeirdML38.4%12.4%
LMArena Coding14171254
BigCodeBench Instruct—46%
BigCodeBench Complete—57.2%
HumanEval+—79.3%

Agentic & Tool Use Not comparable

DeepSeek-V3.1: —, GPT-4: —

BenchmarkDeepSeek-V3.1GPT-4
METR Time Horizons—36.1%

Reasoning DeepSeek-V3.1 leads

DeepSeek-V3.1: 27.9 (#110), GPT-4: 17.8 (#289)

BenchmarkDeepSeek-V3.1GPT-4
LMArena Hard Prompts14171241
DTBench82.7%62.7%
LMCA24.3%17.1%
Epoch Capabilities Index139.92125.89
ForecastBench5857.8
SimpleBench40%—
Kagi LLM Benchmark53.2%—
Chess Puzzles—4%
Mystery Game Puzzles—12%
BIG-Bench Hard—75.1%
HellaSwag—95.3%
WinoGrande—87.5%

Math DeepSeek-V3.1 leads

DeepSeek-V3.1: 38.9 (#122), GPT-4: 10.8 (#309)

BenchmarkDeepSeek-V3.1GPT-4
LMArena Math14201269
OTIS Mock AIME 2024-2025—1.1%
MATH Level 5—23%
GSM8K—92%

Knowledge DeepSeek-V3.1 leads

DeepSeek-V3.1: 43.7 (#90), GPT-4: 18.4 (#282)

BenchmarkDeepSeek-V3.1GPT-4
LMArena Expert14051211
GPQA Diamond—35.7%
Vectara Hallucination Rate5.5%—
MMLU—86.4%
TriviaQA—84.8%

Multilingual DeepSeek-V3.1 leads

DeepSeek-V3.1: 51.6 (#106), GPT-4: 40.6 (#215)

BenchmarkDeepSeek-V3.1GPT-4
LMArena Non-English14001246
LMArena Chinese14691242
LMArena French14471283
LMArena German14111251
LMArena Japanese13781209
LMArena Korean13371184
LMArena Russian14051251
LMArena Spanish14311261

Instruction Following DeepSeek-V3.1 leads

DeepSeek-V3.1: 73.9 (#110), GPT-4: 65.3 (#222)

BenchmarkDeepSeek-V3.1GPT-4
LMArena Instruction Following14001241

Long Context GPT-4 leads

DeepSeek-V3.1: 36.3 (#232), GPT-4: 37.7 (#212)

BenchmarkDeepSeek-V3.1GPT-4
LMArena Longer Query14221244
Fiction.LiveBench52.8%—

Writing & Preference DeepSeek-V3.1 leads

DeepSeek-V3.1: 60.3 (#98), GPT-4: 34.9 (#268)

BenchmarkDeepSeek-V3.1GPT-4
LMArena Text14201263
LMArena Creative Writing14011244
EQ-Bench Creative Writing1436752
LMArena Multi-Turn14081257

Frequently asked questions

Is DeepSeek-V3.1 better than GPT-4?

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 29.1 on the Noometry Index.

Which is cheaper, DeepSeek-V3.1 or GPT-4?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; GPT-4 lists at $30 and $60.

Is DeepSeek-V3.1 or GPT-4 better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

DeepSeek-V3.1 does, with 164K tokens against 8K.

How many benchmarks do DeepSeek-V3.1 and GPT-4 share?

23 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and GPT-4 has 38.

Related comparisons

Go deeper