DataLearner logo

GPT-5vsGemini 2.5-Pro

Across 9 shared benchmarks, GPT-5 leads overall: GPT-5 wins 7, Gemini 2.5-Pro wins 2, with 0 ties and an average score difference of +53.98.

OpenAI
GPT-5

OpenAI · 2025-08-07 · Foundation model

Google Deep Mind
Gemini 2.5-Pro

Google Deep Mind · 2025-06-05 · Reasoning model

GPT-57 wins(78%)(22%)2 winsGemini 2.5-Pro

Benchmark scores

Grouped by capability, sorted by largest gap within each. 9 shared benchmarks.

Math and Reasoning

GPT-5 3/4
BenchmarkGPT-5Gemini 2.5-ProDiff
IMO 2025292 / 9Thinking (No Tools)15.203 / 9Thinking (No Tools)+13.80
IMO 2024114 / 10Thinking (No Tools)192 / 10Thinking (No Tools)-8
IMO-ProofBench592 / 16Thinking (No Tools)55.203 / 16Thinking (No Tools)+3.80
IMO-ProofBench Advanced2011 / 24Thinking (No Tools)17.6014 / 24Thinking (No Tools)+2.40

Coding and Software Engineer

Even 2/2
BenchmarkGPT-5Gemini 2.5-ProDiff
CodeClash1,3602 / 8Normal (With Tools)1,1256 / 8Normal (With Tools)+235
LiveCodeBench55.80149 / 250Normal (No Tools)77.1061 / 250Normal (No Tools)-21.30

Agent Level Benchmark

GPT-5 1/1
BenchmarkGPT-5Gemini 2.5-ProDiff
τ³-Banking22.1085 / 164Thinking High (With Tools)13.66114 / 164Thinking High (With Tools)+8.44

AI Agent - Information Search

GPT-5 1/1
BenchmarkGPT-5Gemini 2.5-ProDiff
BrowseComp54.9041 / 57Thinking (With Tools)7.8056 / 57Thinking (With Tools)+47.10

Writing and Creative Capabilities

GPT-5 1/1
BenchmarkGPT-5Gemini 2.5-ProDiff
Creative Writing1,62436 / 106Normal (No Tools)1,41958 / 106Normal (No Tools)+204.60

Specs

FieldGPT-5Gemini 2.5-Pro
PublisherOpenAIGoogle Deep Mind
Release date2025-08-072025-06-05
Model typeFoundation modelReasoning model
ArchitectureDenseDense
ParametersNot availableNot available
Context length400K1000K
Max output128K64K

API pricing

Prices use DataLearner records when available; missing fields are not inferred.

ItemGPT-5Gemini 2.5-Pro
Text input$1.25 / 1M tokens$1.25 / 1M tokens
Text output$10 / 1M tokens$10 / 1M tokens
Cache read$0.125 / 1M tokens$0.125 / 1M tokens
Cache write$0 / 1M tokensNot public

Summary

  • GPT-5leads in:Math and Reasoning (3/4), Agent Level Benchmark (1/1), AI Agent - Information Search (1/1), Writing and Creative Capabilities (1/1)
  • Tied in:Coding and Software Engineer

On average across the 9 shared benchmarks, GPT-5 scores 53.98 higher.

Largest single-benchmark gap: CodeClash — GPT-5 1,360 vs Gemini 2.5-Pro 1,125 (+235).

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