UCP PlaygroundGemini 3.8 Flash/Models/Gemini 3.8 Flash
InspectorAgentDocs
GoogleGoogle

Gemini 3.8 Flash

Google's newest fast tier (Gemini 3.8 Flash, 2 Sep 2026; OpenRouter lists it as its most capable Flash for agentic, multi-step work). Same price as 3.6 Flash. Newly added: Playground benchmark metrics are still being gathered.

Avg Tokens120,674Avg Duration60.7sTurns to Checkout5.3
CheckoutCartSearchTurnsTokens37.5751008473
Shopping Score64/100
Good

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%37.5%
Cart Rate20%75%
Search Rate10%100%
Turn Efficiency15%84%
Token Efficiency15%73%

Top Stores

StoreCheckout %Cart %
presscoffee.com50%75%
ascentprotein.com25%75%

Known Issues

Metrics Pendinglow

Gemini 3.8 Flash was recently added; its Playground benchmark metrics are still being gathered.

Token Usage

Avg per Session120,674
Fleet Average67,266
vs Fleet+79%
Median (p50)44,780
p90357,416
Prompt / Completion split
Prompt 117,624 (97%) Completion 3,050 (3%)
Daily Average Tokens (last 30 days)
Distribution range
Min10,529p2532,940p5044,780p75134,064p90357,416Max397,995

Test Gemini 3.8 Flash on Your Store

Run a live agent session to see how Gemini 3.8 Flash handles your store's checkout flow end-to-end.

Run Agent Session

Compare With Other Models

GoogleGoogleGemini 3.6 Flash42.1%MetaMetaLlama 3.3 70B39.3%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%AnthropicAnthropicClaude Sonnet 57.2%xAIxAIGrok 4.56.7%DeepSeekDeepSeekDeepSeek V4 Flash5.9%DeepSeekDeepSeekDeepSeek R1 (Reasoning)3.8%Moonshot AIMoonshot AIKimi K33.4%MetaMetaLlama 4 Maverick2.5%AlibabaAlibabaQwen 3.7 Max0%AlibabaAlibabaQwQ 32B (Reasoning)0%
Full comparison view →