UCP PlaygroundDeepSeek V3.2/Models/DeepSeek V3.2
InspectorAgentDocs
DeepSeekDeepSeek

DeepSeek V3.2

The highest checkout rate in the benchmark at 68%. Efficient at 6.2 turns average with low token usage. The trade-off: a 13.1% tool error rate, suggesting it brute-forces through errors rather than avoiding them. Never needs nudging — pushes through autonomously. The best raw completion rate of any model tested.

Avg Tokens65,940Avg Duration47.2sTurns to Checkout6.7
CheckoutCartSearchTurnsTokens20.736.774.76667
Shopping Score43/100
Fair

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%20.7%
Cart Rate20%36.7%
Search Rate10%74.7%
Turn Efficiency15%66%
Token Efficiency15%67%
24.7% of sessions failed with errors.

Top Stores

StoreCheckout %Cart %
••••••••••••••••77.8%77.8%
houseofparfum.nl72%72%
monos.com50%50%
ucp.travel33.3%33.3%
allbirds.com20%20%
snocks.com0%0%
••••••••••••••••0%50%
••••••••••••••••0%0%
••••••••••••••••0%100%
••••••••••••••••0%50%

Known Issues

Tool Error Ratemedium

13.1% error rate — brute-forces through errors rather than avoiding them.

JSON Formattinglow

Occasional issues with tool argument types. Requires extra validation overlays.

Token Usage

Avg per Session65,940
Fleet Average74,927
vs Fleet−12%
Median (p50)30,268
p90144,669
Prompt / Completion split
Prompt 65,201 (99%) Completion 739 (1%)
Daily Average Tokens (last 30 days)
Distribution range
Min2,517p2518,240p5030,268p7558,313p90144,669Max698,476

Test DeepSeek V3.2 on Your Store

Run a live agent session to see how DeepSeek V3.2 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 →