GoogleGemini 3.6 Flash
Google's latest fast tier (Gemini 3.6 Flash, succeeding 3.5 Flash). Newly added — Playground benchmark metrics are still being gathered. The Gemini Flash line targets high-volume, low-latency testing at low token cost.
Avg Tokens140,074Avg Duration29.1sTurns to Checkout11.5
Shopping Score21/100
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 Rate
Cart Rate
Search Rate
Turn Efficiency
Token Efficiency
13.5% of sessions failed with errors.
Top Stores
| Store | Checkout % | Cart % |
|---|---|---|
| •••••••••••••••••••••••••••••••• | 0% | 90% |
| everlane.com | 0% | 50% |
| singon.com.np | 0% | 0% |
| westwing.de | 0% | 80% |
| ••••••••••••••••••••••• | 0% | 100% |
| ••••••••••••••••• | 0% | 0% |
Known Issues
Metrics Pendinglow
Gemini 3.6 Flash was recently added; its Playground benchmark metrics are still being gathered.
Token Usage
Avg per Session140,074
Fleet Average66,698
vs Fleet+110%
Median (p50)42,145
p90441,892
Prompt / Completion split
Prompt 137,120 (98%) Completion 2,954 (2%)
Daily Average Tokens (last 30 days)
Distribution range
Min3,401p2519,073p5042,145p75102,046p90441,892Max1,228,711
Compare With Other Models
MetaLlama 3.3 70B39.3%GoogleGemini 3.5 Flash38.9%
AnthropicClaude Sonnet 4.636.7%
xAIGrok 4.326.3%GoogleGemini 2.5 Flash25.9%AnthropicClaude Opus 4.823.2%
DeepSeekDeepSeek V3.222.1%GoogleGemini 3.1 Pro21.1%GoogleGemini 2.5 Pro20%
OpenAIGPT-4o15.1%OpenAIGPT-5.511.2%xAIGrok 3 Mini (Reasoning)11.1%OpenAIo4-mini (Reasoning)9.5%AnthropicClaude Sonnet 59.4%DeepSeekDeepSeek V4 Pro8.8%DeepSeekDeepSeek V4 Flash6.5%
Moonshot AIKimi K34.5%xAIGrok 4.54.2%DeepSeekDeepSeek R1 (Reasoning)4.1%GoogleGemini 3.6 Flash3.8%MetaLlama 4 Maverick2.7%AnthropicClaude Opus 51.8%
AlibabaQwen 3.7 Max0%AlibabaQwQ 32B (Reasoning)0%