AlibabaQwen 3.7 Max
Alibaba's Qwen 3.7 Max flagship (1M context). Newly added — Playground benchmark metrics are still being gathered. Returns the Qwen line to the lineup (QwQ 32B is retired).
Avg Tokens70,063Avg Duration26.8s
Shopping Score29/100
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
21.4% of sessions failed with errors.
Top Stores
| Store | Checkout % | Cart % |
|---|---|---|
| allbirds.com | 0% | 50% |
| everlane.com | 0% | 0% |
| ••••••••••••••••• | 0% | 50% |
Known Issues
Metrics Pendinglow
Qwen 3.7 Max was recently added; its Playground benchmark metrics are still being gathered.
Token Usage
Avg per Session70,063
Fleet Average66,759
vs Fleet+5%
Median (p50)29,987
p90147,634
Prompt / Completion split
Prompt 68,957 (98%) Completion 1,107 (2%)
Daily Average Tokens (last 30 days)
Distribution range
Min7,652p2515,664p5029,987p75110,941p90147,634Max346,079
Compare With Other Models
MetaLlama 3.3 70B39.3%
GoogleGemini 3.5 Flash39%
AnthropicClaude Sonnet 4.636.8%GoogleGemini 2.5 Flash26.4%
xAIGrok 4.326.3%AnthropicClaude Opus 4.823.2%
DeepSeekDeepSeek V3.222.1%GoogleGemini 3.1 Pro21.1%GoogleGemini 2.5 Pro20%
OpenAIGPT-4o15.5%OpenAIGPT-5.511.2%xAIGrok 3 Mini (Reasoning)11.1%AnthropicClaude Sonnet 510%OpenAIo4-mini (Reasoning)9.5%DeepSeekDeepSeek V4 Pro9%
Moonshot AIKimi K34.8%xAIGrok 4.54.5%DeepSeekDeepSeek R1 (Reasoning)4.1%DeepSeekDeepSeek V4 Flash3.3%MetaLlama 4 Maverick2.7%GoogleGemini 3.6 Flash2%AnthropicClaude Opus 51.8%AlibabaQwen 3.7 Max0%AlibabaQwQ 32B (Reasoning)0%