Compare / GPT-4o (2024-05-13) vs GPT-5

GPT-4o (2024-05-13) vs GPT-5

Which is cheaper, which is more capable, and which does better at each kind of work, from 13 results on 3 sources that measured both models.

GPT-4o (2024-05-13)
OpenAI · profile
GPT-5
OpenAI · profile
Results compared
13
Shared sources
3

GPT-4o (2024-05-13) or GPT-5? The short answer

  • GPT-5 is cheaper: $3.44 against $7.50 per million tokens, 2.2 times less.
  • GPT-5 scores higher on the Artificial Analysis Intelligence Index: 23.0 against 7.3.
  • On our business benchmarks, GPT-5 ranks higher for reasoning and knowledge and writing.

At a glance

GPT-4o (2024-05-13)GPT-5
Price per million tokens$5.00 in · $15.00 out$1.25 in · $10.00 out
Blended (3 in : 1 out)$7.50$3.44
Cheapest host, blended$7.50 (Azure)$3.44 (Azure)
Intelligence Index7.323.0
Spring Prompt overall––
Output speed, tokens a second––
Context window128,000 tokens400,000 tokens
WeightsClosedClosed
Developer based inthe USthe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.

Use caseGPT-4o (2024-05-13)GPT-5
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls not measured 75 of 161
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 44 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 182 of 195 72 of 195
WritingWhat people prefer in blind comparisons, and judged writing quality 88 of 187 67 of 187
Sticking to the factsSummarising without inventing things, and factual answers not measured 100 of 153

Every shared result

BenchmarkMetricGPT-4o (2024-05-13)GPT-5
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,3221,413
Arena (formerly LMArena)reportedCreative writingArena rating 1,3381,373
Arena (formerly LMArena)reportedExpert promptsArena rating 1,3111,460
Arena (formerly LMArena)reportedInstruction followingArena rating 1,3261,410
Arena (formerly LMArena)reportedOverallArena rating 1,3461,435
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,3451,397
Artificial AnalysisreportedArtificial Analysis Coding Indexindex score 24.237.8
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 7.3023.0
Artificial AnalysisreportedGPQA Diamond% of questions 52.6%85.4%
Artificial AnalysisreportedHumanity's Last Exam% of questions 1.8%28.5%
UGI LeaderboardreportedRequested-length error% off the requested word count 12.0%58.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.330.39
UGI LeaderboardreportedWriting scorescore out of 100 63.453.5

Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.

Quick answers

Is GPT-4o (2024-05-13) better than GPT-5?

It depends on the task. Among models available today, on our benchmarks and licensed sources, GPT-5 ranks higher for reasoning and knowledge and writing.

Which is cheaper, GPT-4o (2024-05-13) or GPT-5?

GPT-5 costs $3.44 per million tokens (three input to one output), against $7.50 for GPT-4o (2024-05-13).

Run GPT-4o (2024-05-13) and GPT-5 on your own prompt

Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.