UCP PlaygroundGemini 2.5 Pro/Models/Gemini 2.5 Pro
InspectorAgentDocs
GoogleGoogle

Gemini 2.5 Pro

Google's previous-gen flagship. Highest failure rate among Google models (16%) with a near-10% tool error rate. When it succeeds, checkout takes 8.5 turns on average. Being superseded by Gemini 3.1 Pro which outperforms it on every metric.

Avg Tokens48,775Avg Duration37.8sTurns to Checkout9
CheckoutCartSearchTurnsTokens19.839.268.83841
Shopping Score34/100
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%19.8%
Cart Rate20%39.2%
Search Rate10%68.8%
Turn Efficiency15%38%
Token Efficiency15%41%
30.8% of sessions failed with errors.

Top Stores

StoreCheckout %Cart %
••••••••••••••••75%75%
pier1.com66.7%66.7%
ucp.travel58.3%58.3%
roxy.com50%50%
••••••••••••••••50%66.7%
••••••••••••••••50%100%
••••••••••••••••50%50%
houseofparfum.nl31.3%37.5%
••••••••••••••••20%70%
allbirds.com20%20%

Known Issues

High Failure Ratehigh

16% of sessions fail — highest among Google models. Primarily timeout and connection issues.

Tool Error Ratemedium

9.9% error rate on tool calls.

Token Usage

Avg per Session48,775
Fleet Average74,927
vs Fleet−35%
Median (p50)30,385
p90110,026
Prompt / Completion split
Prompt 46,722 (96%) Completion 2,052 (4%)
Daily Average Tokens (last 30 days)
Distribution range
Min0p2512,928p5030,385p7566,581p90110,026Max287,678

Test Gemini 2.5 Pro on Your Store

Run a live agent session to see how Gemini 2.5 Pro handles your store's checkout flow end-to-end.

Run Agent Session

Compare With Other Models

MetaMetaLlama 3.3 70B39.3%GoogleGoogleGemini 3.5 Flash38.1%AnthropicAnthropicClaude Sonnet 4.634.7%xAIxAIGrok 4.326.3%GoogleGoogleGemini 2.5 Flash23.3%AnthropicAnthropicClaude Opus 4.822.3%AlibabaAlibabaQwen 3.8 Flash22.2%DeepSeekDeepSeekDeepSeek V3.220.7%GoogleGoogleGemini 2.5 Pro19.8%GoogleGoogleGemini 3.1 Pro19.6%OpenAIOpenAIGPT-4o15%DeepSeekDeepSeekDeepSeek V4.1 Flash14.3%xAIxAIGrok 3 Mini (Reasoning)11.1%OpenAIOpenAIGPT-5.510.2%OpenAIOpenAIo4-mini (Reasoning)9.1%AnthropicAnthropicClaude Opus 59%xAIxAIGrok 4.58.1%AnthropicAnthropicClaude Sonnet 57.7%DeepSeekDeepSeekDeepSeek V4 Pro7.7%DeepSeekDeepSeekDeepSeek V4 Flash7.5%GoogleGoogleGemini 3.8 Flash6.7%DeepSeekDeepSeekDeepSeek R1 (Reasoning)3.6%Moonshot AIMoonshot AIKimi K33.1%AlibabaAlibabaQwen 3.7 Max2.6%MetaMetaLlama 4 Maverick2.3%GoogleGoogleGemini 3.6 Flash1.1%GoogleGoogleGemini 3.7 Flash0%OpenAIOpenAIGPT-6 Luna0%MetaMetaMuse Spark 1.30%AlibabaAlibabaQwQ 32B (Reasoning)0%
Full comparison view →