Noometry

Model comparison

GPT-4 vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 29.1 on the Noometry Index.

Last verified . 13 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Step 5 Preview StepFun

47.9

Rank #58 Confirmed

Summary

  • They share 13 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Step 5 Preview leads 46.1 to 10.8.
  • Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $30 / $60 for GPT-4.
  • Step 5 Preview accepts more context: 1.02M tokens versus 8K.

Side by side

GPT-4Step 5 Preview
ProviderOpenAIStepFun
Noometry Index29.147.9
Released2023-03-142026-09-16
WeightsProprietaryProprietary
Context window8K1.02M
Max output8K66K
Input $ / M tokens$30$1
Output $ / M tokens$60$2.70
Results tracked3818

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

Category by category

Coding Step 5 Preview leads

GPT-4: 31.6 (#283), Step 5 Preview: 51.8 (#36)

BenchmarkGPT-4Step 5 Preview
LMArena Coding12541480
LMArena WebDev—1564
SciCode—58.9%
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Step 5 Preview: —

BenchmarkGPT-4Step 5 Preview
METR Time Horizons36.1%—

Reasoning Step 5 Preview leads

GPT-4: 17.8 (#289), Step 5 Preview: 40.0 (#57)

BenchmarkGPT-4Step 5 Preview
LMArena Hard Prompts12411465
CritPt—20.9%
Chess Puzzles4%—
Mystery Game Puzzles12%—
DTBench62.7%—
LMCA17.1%—
BIG-Bench Hard75.1%—
Epoch Capabilities Index125.89—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Step 5 Preview leads

GPT-4: 10.8 (#309), Step 5 Preview: 46.1 (#72)

BenchmarkGPT-4Step 5 Preview
LMArena Math12691470
OTIS Mock AIME 2024-20251.1%—
ProofBench—42%
MATH Level 523%—
GSM8K92%—

Knowledge Step 5 Preview leads

GPT-4: 18.4 (#282), Step 5 Preview: 41.2 (#112)

BenchmarkGPT-4Step 5 Preview
LMArena Expert12111470
GPQA Diamond35.7%—
MMLU86.4%—
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, Step 5 Preview: 41.0 (#41)

BenchmarkGPT-4Step 5 Preview
LMArena Vision—1267

Multilingual Step 5 Preview leads

GPT-4: 40.6 (#215), Step 5 Preview: 53.8 (#54)

BenchmarkGPT-4Step 5 Preview
LMArena Non-English12461432
LMArena Chinese12421519
LMArena Russian12511436
LMArena Spanish12611439
LMArena French1283—
LMArena German1251—
LMArena Japanese1209—
LMArena Korean1184—

Instruction Following Step 5 Preview leads

GPT-4: 65.3 (#222), Step 5 Preview: 76.0 (#50)

BenchmarkGPT-4Step 5 Preview
LMArena Instruction Following12411444

Long Context Step 5 Preview leads

GPT-4: 37.7 (#212), Step 5 Preview: 44.5 (#64)

BenchmarkGPT-4Step 5 Preview
LMArena Longer Query12441455

Writing & Preference Step 5 Preview leads

GPT-4: 34.9 (#268), Step 5 Preview: 62.8 (#71)

BenchmarkGPT-4Step 5 Preview
LMArena Text12631442
LMArena Creative Writing12441410
LMArena Multi-Turn12571447
EQ-Bench Creative Writing752—

Frequently asked questions

Is GPT-4 better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or Step 5 Preview?

Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 8K.

How many benchmarks do GPT-4 and Step 5 Preview share?

13 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Step 5 Preview has 18.

Related comparisons

Go deeper