GPT-5vsGPT-4.5

Across 3 shared benchmarks, GPT-5 leads overall: GPT-5 wins 3, GPT-4.5 wins 0, with 0 ties and an average score difference of +24.30.

OpenAI
GPT-5

OpenAI · 2025-08-07 · Foundation model

OpenAI
GPT-4.5

OpenAI · 2025-02-28 · Chat model

GPT-53 wins(100%)(0%)0 winsGPT-4.5

Benchmark scores

Grouped by capability, sorted by largest gap within each. 3 shared benchmarks.

Coding and Software Engineer

GPT-5 1/1
BenchmarkGPT-5GPT-4.5Diff
SWE-bench Verified72.8046 / 10838100 / 108+34.80

General Knowledge

GPT-5 1/1
BenchmarkGPT-5GPT-4.5Diff
GPQA Diamond87.3037 / 17871.40105 / 178+15.90

Math and Reasoning

GPT-5 1/1
BenchmarkGPT-5GPT-4.5Diff
Simple Bench56.708 / 2734.5020 / 27+22.20

Specs

FieldGPT-5GPT-4.5
PublisherOpenAIOpenAI
Release date2025-08-072025-02-28
Model typeFoundation modelChat model
ArchitectureDenseDense
ParametersNot availableNot available
Context length400K128K
Max output128KNot available

Summary

  • GPT-5leads in:Coding and Software Engineer (1/1), General Knowledge (1/1), Math and Reasoning (1/1)

On average across the 3 shared benchmarks, GPT-5 scores 24.30 higher.

Largest single-benchmark gap: SWE-bench Verified — GPT-5 72.80 vs GPT-4.5 38 (+34.80).

Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.