Noometry

Model comparison

GPT-4 vs GPT-5.3 Chat

GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 29.1 on the Noometry Index.

Last verified . 18 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

GPT-5.3 Chat OpenAI

42.8

Rank #109 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GPT-4 scores higher in 0 categories and GPT-5.3 Chat in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-5.3 Chat leads 63.1 to 34.9.
  • GPT-5.3 Chat is cheaper at $1.75 / $14 per million input/output tokens, against $30 / $60 for GPT-4.
  • GPT-5.3 Chat accepts more context: 128K tokens versus 8K.

Side by side

GPT-4GPT-5.3 Chat
ProviderOpenAIOpenAI
Noometry Index29.142.8
Released2023-03-142026-03-03
WeightsProprietaryProprietary
Context window8K128K
Max output8K16K
Input $ / M tokens$30$1.75
Output $ / M tokens$60$14
Results tracked3818

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

Category by category

Coding GPT-5.3 Chat leads

GPT-4: 31.6 (#283), GPT-5.3 Chat: 41.4 (#124)

BenchmarkGPT-4GPT-5.3 Chat
LMArena Coding12541408
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, GPT-5.3 Chat: —

BenchmarkGPT-4GPT-5.3 Chat
METR Time Horizons36.1%—

Reasoning GPT-5.3 Chat leads

GPT-4: 17.8 (#289), GPT-5.3 Chat: 28.5 (#102)

BenchmarkGPT-4GPT-5.3 Chat
LMArena Hard Prompts12411399
Chess Puzzles4%—
Mystery Game Puzzles12%—
DTBench62.7%—
LMCA17.1%—
BIG-Bench Hard75.1%—
Epoch Capabilities Index125.89—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math GPT-5.3 Chat leads

GPT-4: 10.8 (#309), GPT-5.3 Chat: 38.2 (#142)

BenchmarkGPT-4GPT-5.3 Chat
LMArena Math12691389
OTIS Mock AIME 2024-20251.1%—
MATH Level 523%—
GSM8K92%—

Knowledge GPT-5.3 Chat leads

GPT-4: 18.4 (#282), GPT-5.3 Chat: 38.8 (#140)

BenchmarkGPT-4GPT-5.3 Chat
LMArena Expert12111397
GPQA Diamond35.7%—
MMLU86.4%—
TriviaQA84.8%—

Multilingual GPT-5.3 Chat leads

GPT-4: 40.6 (#215), GPT-5.3 Chat: 50.3 (#124)

BenchmarkGPT-4GPT-5.3 Chat
LMArena Non-English12461382
LMArena Chinese12421432
LMArena French12831397
LMArena German12511384
LMArena Japanese12091352
LMArena Korean11841346
LMArena Russian12511400
LMArena Spanish12611371

Instruction Following GPT-5.3 Chat leads

GPT-4: 65.3 (#222), GPT-5.3 Chat: 72.8 (#129)

BenchmarkGPT-4GPT-5.3 Chat
LMArena Instruction Following12411378

Long Context GPT-5.3 Chat leads

GPT-4: 37.7 (#212), GPT-5.3 Chat: 42.6 (#120)

BenchmarkGPT-4GPT-5.3 Chat
LMArena Longer Query12441396

Writing & Preference GPT-5.3 Chat leads

GPT-4: 34.9 (#268), GPT-5.3 Chat: 63.1 (#68)

BenchmarkGPT-4GPT-5.3 Chat
LMArena Text12631389
LMArena Creative Writing12441355
EQ-Bench Creative Writing7521690
LMArena Multi-Turn12571412

Frequently asked questions

Is GPT-4 better than GPT-5.3 Chat?

GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or GPT-5.3 Chat?

GPT-5.3 Chat is cheaper. It lists at $1.75 per million input tokens and $14 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or GPT-5.3 Chat better for coding?

GPT-5.3 Chat scores higher on coding benchmarks: 41.4 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

GPT-5.3 Chat does, with 128K tokens against 8K.

How many benchmarks do GPT-4 and GPT-5.3 Chat share?

18 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and GPT-5.3 Chat has 18.

Related comparisons

Go deeper