Noometry

Model comparison

GPT-4 vs GPT-4 Turbo

GPT-4 Turbo is the stronger model overall, scoring 30.3 to 28.9 on the Noometry Index.

Last verified . 31 shared benchmarks.

GPT-4 OpenAI

28.9

Rank #308 Confirmed

GPT-4 Turbo OpenAI

30.3

Rank #281 Confirmed

Summary

  • They share 31 benchmarks with published results for both. GPT-4 scores higher in 3 categories and GPT-4 Turbo in 5 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-4 Turbo leads 47.9 to 35.0.
  • The biggest single-benchmark swing is MATH Level 5: 23% for GPT-4 and 46.7% for GPT-4 Turbo.
  • GPT-4 Turbo is cheaper at $10 / $30 per million input/output tokens, against $30 / $60 for GPT-4.
  • GPT-4 Turbo accepts more context: 128K tokens versus 8K.

Side by side

GPT-4GPT-4 Turbo
ProviderOpenAIOpenAI
Noometry Index28.930.3
Released2023-03-142023-11-06
WeightsProprietaryProprietary
Context window8K128K
Max output8K4K
Input $ / M tokens$30$10
Output $ / M tokens$60$30
Results tracked3836

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

Category by category

Coding GPT-4 Turbo leads

GPT-4: 31.2 (#277), GPT-4 Turbo: 33.4 (#247)

BenchmarkGPT-4GPT-4 Turbo
WeirdML12.4%18%
BigCodeBench Instruct46%48.2%
LMArena Coding12541268
BigCodeBench Complete57.2%58.2%
HumanEval+79.3%86.6%
MBPP+—73.3%

Agentic & Tool Use Not comparable

GPT-4: —, GPT-4 Turbo: —

BenchmarkGPT-4GPT-4 Turbo
METR Time Horizons36.1%36.7%

Reasoning GPT-4 leads

GPT-4: 17.3 (#285), GPT-4 Turbo: 14.9 (#311)

BenchmarkGPT-4GPT-4 Turbo
Chess Puzzles4%6%
LMArena Hard Prompts12411251
DTBench62.7%61.6%
LMCA17.1%9.8%
Epoch Capabilities Index125.88127.25
ForecastBench57.859.4
SimpleBench—25.1%
Mystery Game Puzzles12%—
BIG-Bench Hard75.1%—
HellaSwag95.3%—
WinoGrande87.5%—

Math GPT-4 leads

GPT-4: 10.1 (#304), GPT-4 Turbo: 8.6 (#316)

BenchmarkGPT-4GPT-4 Turbo
OTIS Mock AIME 2024-20251.1%6.7%
LMArena Math12691272
MATH Level 523%46.7%
FrontierMath (Tiers 1-3)—0.7%
GSM8K92%—

Knowledge GPT-4 Turbo leads

GPT-4: 18.4 (#277), GPT-4 Turbo: 24.3 (#263)

BenchmarkGPT-4GPT-4 Turbo
GPQA Diamond35.7%46.6%
LMArena Expert12111223
MMLU86.4%81.3%
Confabulations—28.4%
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, GPT-4 Turbo: 30.0 (#104)

BenchmarkGPT-4GPT-4 Turbo
LMArena Vision—1090

Multilingual Too close to call

GPT-4: 40.8 (#210), GPT-4 Turbo: 40.7 (#211)

BenchmarkGPT-4GPT-4 Turbo
LMArena Non-English12461245
LMArena Chinese12421242
LMArena French12821275
LMArena German12511259
LMArena Japanese12091194
LMArena Korean11841187
LMArena Russian12511259
LMArena Spanish12611260

Instruction Following Too close to call

GPT-4: 65.5 (#217), GPT-4 Turbo: 66.0 (#211)

BenchmarkGPT-4GPT-4 Turbo
LMArena Instruction Following12411250

Long Context Too close to call

GPT-4: 37.7 (#207), GPT-4 Turbo: 38.0 (#200)

BenchmarkGPT-4GPT-4 Turbo
LMArena Longer Query12441254

Writing & Preference GPT-4 Turbo leads

GPT-4: 35.0 (#263), GPT-4 Turbo: 47.9 (#201)

BenchmarkGPT-4GPT-4 Turbo
LMArena Text12631272
LMArena Creative Writing12441269
LMArena Multi-Turn12571267
EQ-Bench Creative Writing752—

Frequently asked questions

Is GPT-4 better than GPT-4 Turbo?

GPT-4 Turbo is the stronger model overall, scoring 30.3 to 28.9 on the Noometry Index.

Which is cheaper, GPT-4 or GPT-4 Turbo?

GPT-4 Turbo is cheaper. It lists at $10 per million input tokens and $30 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or GPT-4 Turbo better for coding?

GPT-4 Turbo scores higher on coding benchmarks: 33.4 versus 31.2 in the Noometry coding category.

Which has the bigger context window?

GPT-4 Turbo does, with 128K tokens against 8K.

How many benchmarks do GPT-4 and GPT-4 Turbo share?

31 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and GPT-4 Turbo has 36.

Related comparisons

Go deeper