DataLearner logo

GPT-5vsGemini 2.5-Pro

Across 20 shared benchmarks, GPT-5 leads overall: GPT-5 wins 18, Gemini 2.5-Pro wins 2, with 0 ties and an average score difference of +23.48.

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-518 wins(90%)(10%)2 winsGemini 2.5-Pro

Benchmark scores

Grouped by capability, sorted by largest gap within each. 20 shared benchmarks.

Math and Reasoning

GPT-5 6/7
BenchmarkGPT-5Gemini 2.5-ProDiff
IMO 2025292 / 915.203 / 9+13.80
FrontierMath24.8015 / 601123 / 60+13.80
AIME202599.609 / 1078844 / 107+11.60
FrontierMath - Tier 412.5029 / 80Thinking High (No Tools)2.1056 / 80Normal (No Tools)+10.40
IMO 2024114 / 10192 / 10-8
IMO-ProofBench592 / 1655.203 / 16+3.80
IMO-ProofBench Advanced202 / 817.604 / 8+2.40

General Knowledge

GPT-5 4/4
BenchmarkGPT-5Gemini 2.5-ProDiff
ARC-AGI65.7033 / 683750 / 68+28.70
HLE35.2073 / 17221.60112 / 172+13.60
ARC-AGI-29.9040 / 624.9047 / 62+5
GPQA Diamond87.3040 / 18786.4045 / 187+0.90

Agent Level Benchmark

GPT-5 2/2
BenchmarkGPT-5Gemini 2.5-ProDiff
τ²-Bench - Telecom95.8013 / 355432 / 35+41.80
Aider-Polyglot881 / 59Thinking High (No Tools)83.104 / 59Thinking (No Tools, 32K Budget)+4.90

Coding and Software Engineer

GPT-5 2/2
BenchmarkGPT-5Gemini 2.5-ProDiff
CodeClash1,3602 / 8Normal (With Tools)1,1256 / 8Normal (With Tools)+235
SWE-bench Verified72.8050 / 11267.2072 / 112+5.60

AI Agent - Information Search

GPT-5 1/1
BenchmarkGPT-5Gemini 2.5-ProDiff
BrowseComp54.9039 / 537.8052 / 53+47.10

AI Agent - Tool Usage

GPT-5 1/1
BenchmarkGPT-5Gemini 2.5-ProDiff
Terminal-Bench43.808 / 3525.3028 / 35+18.50

Commonsense Reasoning

Gemini 2.5-Pro 1/1
BenchmarkGPT-5Gemini 2.5-ProDiff
Simple Bench56.7020 / 63Thinking High (No Tools)62.4011 / 63Thinking (No Tools)-5.70

Instruction Following

GPT-5 1/1
BenchmarkGPT-5Gemini 2.5-ProDiff
IF Bench73.109 / 304929 / 30+24.10

Multimodal Understanding

GPT-5 1/1
BenchmarkGPT-5Gemini 2.5-ProDiff
MMMU84.206 / 298210 / 29+2.20

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 tokensNot public
Cache write$0 / 1M tokensNot public

Summary

  • GPT-5leads in:Math and Reasoning (6/7), General Knowledge (4/4), Agent Level Benchmark (2/2), Coding and Software Engineer (2/2), AI Agent - Information Search (1/1), AI Agent - Tool Usage (1/1), Instruction Following (1/1), Multimodal Understanding (1/1)
  • Gemini 2.5-Proleads in:Commonsense Reasoning (1/1)

On average across the 20 shared benchmarks, GPT-5 scores 23.48 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.