UCP PlaygroundGrok 4.3/Models/Grok 4.3
InspectorAgentDocs
xAIxAI

Grok 4.3 Retired

This model is no longer available to run. Its stats below reflect past sessions and are kept for reference.

xAI's Grok 4.3 (this slot also carries earlier Grok 4 runs). Standout reliability in our benchmark — near-zero session failures and a very low tool error rate — with an efficient checkout path; latency was the main drawback, the slowest of the frontier models. Retired: superseded by Grok 4.5.

Avg Tokens35,601Avg Duration45.4sTurns to Checkout6.5
CheckoutCartSearchTurnsTokens26.333.164.46961
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%26.3%
Cart Rate20%33.1%
Search Rate10%64.4%
Turn Efficiency15%69%
Token Efficiency15%61%
35.6% of sessions failed with errors.

Top Stores

StoreCheckout %Cart %
•••••••••••••••••••100%100%
ucp.travel100%100%
•••••••••••••••80%100%
••••••••••••••••••••••••••••••••50%100%
houseofparfum.nl46.4%50%
everlane.com33.3%33.3%
allbirds.com0%0%
•••••••••••••••••••••••••••••0%0%
•••••••••••••••••••••••••••••0%0%
••••••••••••••••••••••••••••••••0%0%

Known Issues

High Latencymedium

84 seconds average per session — slowest frontier model by a significant margin.

Token Usage

Avg per Session35,601
Fleet Average66,570
vs Fleet−47%
Median (p50)22,188
p9093,360
Prompt / Completion split
Prompt 33,765 (95%) Completion 1,836 (5%)
No daily trend data yet. Run more sessions to see token usage over time.
Distribution range
Min0p259,814p5022,188p7542,505p9093,360Max401,007

Test Grok 4.3 on Your Store

Run a live agent session to see how Grok 4.3 handles your store's checkout flow end-to-end.

Run Agent Session

Compare With Other Models

MetaMetaLlama 3.3 70B39.3%GoogleGoogleGemini 3.5 Flash39%AnthropicAnthropicClaude Sonnet 4.636.9%GoogleGoogleGemini 2.5 Flash26.5%xAIxAIGrok 4.326.3%AnthropicAnthropicClaude Opus 4.823.3%DeepSeekDeepSeekDeepSeek V3.222.1%GoogleGoogleGemini 3.1 Pro21.3%GoogleGoogleGemini 2.5 Pro20.1%OpenAIOpenAIGPT-4o15.6%OpenAIOpenAIGPT-5.511.3%AnthropicAnthropicClaude Sonnet 511.1%xAIxAIGrok 3 Mini (Reasoning)11.1%OpenAIOpenAIo4-mini (Reasoning)9.6%DeepSeekDeepSeekDeepSeek V4 Pro9%Moonshot AIMoonshot AIKimi K35%xAIxAIGrok 4.54.5%DeepSeekDeepSeekDeepSeek R1 (Reasoning)4.1%DeepSeekDeepSeekDeepSeek V4 Flash3.4%MetaMetaLlama 4 Maverick2.7%GoogleGoogleGemini 3.6 Flash2%AnthropicAnthropicClaude Opus 52%AlibabaAlibabaQwen 3.7 Max0%AlibabaAlibabaQwQ 32B (Reasoning)0%
Full comparison view →