DeepSeekDeepSeek V4.1 Flash
DeepSeek's V4.1 Flash (10 Sep 2026; about $0.30/$1.20 per M tokens), succeeding V4 Flash. Newly added: Playground benchmark metrics are still being gathered.
Avg Tokens0Avg Duration0ms
Shopping Score15/100
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
Top Stores
Not enough store data yet.
Known Issues
Metrics Pendinglow
DeepSeek V4.1 Flash was recently added; its Playground benchmark metrics are still being gathered.
Token Usage
Avg per Session0
Fleet Average67,270
vs Fleet−100%
Median (p50)0
p900
Prompt / Completion split
Prompt 0 (0%) Completion 0 (100%)
No daily trend data yet. Run more sessions to see token usage over time.
Distribution range
Min0p250p500p750p900Max0
Compare With Other Models
GoogleGemini 3.6 Flash42.2%
MetaLlama 3.3 70B39.3%GoogleGemini 3.5 Flash38.5%GoogleGemini 3.8 Flash37.5%
AnthropicClaude Sonnet 4.635.9%
xAIGrok 4.326.3%GoogleGemini 2.5 Flash25.2%AnthropicClaude Opus 4.822.9%DeepSeekDeepSeek V3.222%GoogleGemini 3.1 Pro20.6%GoogleGemini 2.5 Pro19.9%
OpenAIGPT-4o15%xAIGrok 3 Mini (Reasoning)11.1%OpenAIGPT-5.510.8%OpenAIo4-mini (Reasoning)9.2%AnthropicClaude Opus 58.6%DeepSeekDeepSeek V4 Pro8.3%AnthropicClaude Sonnet 57.2%xAIGrok 4.56.7%DeepSeekDeepSeek V4 Flash5.9%DeepSeekDeepSeek R1 (Reasoning)3.8%
Moonshot AIKimi K33.4%MetaLlama 4 Maverick2.5%
AlibabaQwen 3.7 Max0%AlibabaQwQ 32B (Reasoning)0%