UCP PlaygroundGPT-4o/Models/GPT-4o
InspectorAgentDocs
OpenAIOpenAI

GPT-4o

OpenAI's workhorse model. Fast (15.6s avg) and token-efficient but lower checkout completion than frontier models. Moderate tool error rate (8.4%). Never needs nudging — either completes or gives up cleanly. Good for high-volume, cost-sensitive benchmarking where speed matters more than checkout depth.

Avg Tokens34,077Avg Duration16.4sTurns to Checkout8.2
CheckoutCartSearchTurnsTokens1536.172.54830
Shopping Score32/100
Weak

Scores computed from real agent sessions against live UCP-enabled stores. Not estimated — every data point is from an actual tool call, checkout attempt, and store response.

Shopping Score Breakdown

Checkout Rate40%15%
Cart Rate20%36.1%
Search Rate10%72.5%
Turn Efficiency15%48%
Token Efficiency15%30%
26.6% of sessions failed with errors.

Top Stores

StoreCheckout %Cart %
everlane.com61.5%61.5%
allbirds.com33.3%33.3%
•••••••••••••••33.3%33.3%
houseofparfum.nl30.8%38.5%
ucp.travel28.6%28.6%
kyliecosmetics.com20%20%
••••••••••••••••••••••••••••••••9.1%45.5%
•••••••••••••••••••8.3%91.7%
••••••••••••••••••••••••••0%50%
••••••••••••••••••••••••••••••••0%0%

Known Issues

Low Checkout Completionmedium

33% checkout rate despite fast execution. Gives up rather than retrying on errors.

Moderate Error Ratemedium

8.4% tool error rate — higher than Claude and Gemini models.

Token Usage

Avg per Session34,077
Fleet Average68,722
vs Fleet−50%
Median (p50)22,074
p9085,285
Prompt / Completion split
Prompt 33,535 (98%) Completion 542 (2%)
Daily Average Tokens (last 30 days)
Distribution range
Min0p258,169p5022,074p7539,124p9085,285Max437,563

Test GPT-4o on Your Store

Run a live agent session to see how GPT-4o handles your store's checkout flow end-to-end.

Run Agent Session

Compare With Other Models

MetaMetaLlama 3.3 70B39.3%GoogleGoogleGemini 3.6 Flash38.6%GoogleGoogleGemini 3.5 Flash38.5%GoogleGoogleGemini 3.8 Flash37.5%AnthropicAnthropicClaude Sonnet 4.635.9%xAIxAIGrok 4.326.3%GoogleGoogleGemini 2.5 Flash25.2%AnthropicAnthropicClaude Opus 4.822.9%DeepSeekDeepSeekDeepSeek V3.222%GoogleGoogleGemini 3.1 Pro20.6%GoogleGoogleGemini 2.5 Pro19.9%OpenAIOpenAIGPT-4o15%xAIxAIGrok 3 Mini (Reasoning)11.1%OpenAIOpenAIGPT-5.510.8%OpenAIOpenAIo4-mini (Reasoning)9.2%AnthropicAnthropicClaude Opus 58.6%DeepSeekDeepSeekDeepSeek V4 Pro8.3%xAIxAIGrok 4.56.7%DeepSeekDeepSeekDeepSeek V4 Flash5.9%AnthropicAnthropicClaude Sonnet 54.3%DeepSeekDeepSeekDeepSeek R1 (Reasoning)3.8%Moonshot AIMoonshot AIKimi K33.4%MetaMetaLlama 4 Maverick2.5%OpenAIOpenAIGPT-6 Luna0%AlibabaAlibabaQwen 3.7 Max0%AlibabaAlibabaQwQ 32B (Reasoning)0%
Full comparison view →