GPT-5vsGPT-4o(2025-03-27)

Across 3 shared benchmarks, GPT-5 leads overall: GPT-5 wins 3, GPT-4o(2025-03-27) wins 0, with 0 ties and an average score difference of +50.07.

OpenAI
GPT-5

OpenAI · 2025-08-07 · Foundation model

OpenAI
GPT-4o(2025-03-27)

OpenAI · 2025-03-27 · Chat model

GPT-53 wins(100%)(0%)0 winsGPT-4o(2025-03-27)

Benchmark scores

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

General Knowledge

GPT-5 2/2
BenchmarkGPT-5GPT-4o(2025-03-27)Diff
ARC-AGI65.7030 / 658.8060 / 65+56.90
GPQA Diamond87.3037 / 17866.90124 / 178+20.40

Math and Reasoning

GPT-5 1/1
BenchmarkGPT-5GPT-4o(2025-03-27)Diff
AIME202599.609 / 10626.70101 / 106+72.90

Specs

FieldGPT-5GPT-4o(2025-03-27)
PublisherOpenAIOpenAI
Release date2025-08-072025-03-27
Model typeFoundation modelChat model
ArchitectureDenseDense
ParametersNot availableNot available
Context length400K128K
Max output128K4K

Summary

  • GPT-5leads in:General Knowledge (2/2), Math and Reasoning (1/1)

On average across the 3 shared benchmarks, GPT-5 scores 50.07 higher.

Largest single-benchmark gap: AIME2025 — GPT-5 99.60 vs GPT-4o(2025-03-27) 26.70 (+72.90).

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