Anthropic

Claude Sonnet 5

Anthropic's latest balanced model (Claude Sonnet 5, succeeding the Sonnet 4.x line). Newly added — Playground benchmark metrics are still being gathered. The Sonnet line historically pairs a strong multi-turn checkout flow with faster, more token-efficient responses than Opus.

Avg tokens per run: 224,261
Avg duration: 45.0s
Turns to checkout: 18.4

Start a run with Claude Sonnet 5 Compare

Shopping score

24/100Weak

Scores come from runs on UCP stores, not estimates: every figure is a tool call, a checkout attempt or a store’s answer.

Shopping score breakdown

Checkout rate40%10.8%
Cart rate20%54.2%
Search rate10%92.2%
Turn efficiency15%0%
Token efficiency15%0%

7.8% of runs failed with errors.

Top stores

Development stores are hidden.

Store	Checkout	Cart
store hidden	100%	100%
store hidden	100%	100%
store hidden	80%	100%
store hidden	46.2%	100%
store hidden	20%	20%
store hidden	0%	0%
store hidden	0%	0%
awaytravel.com	0%	100%
mypetcarnivore.com	0%	100%
store hidden	0%	0%

Known issues

LowMetrics Pending
Claude Sonnet 5 was recently added; its Playground benchmark metrics are still being gathered.

Token usage

Avg per run: 224,261
Average of all models: 77,803
Against the average: +188%
Median (p50): 106,036
p90: 416,606

Prompt and completion

Prompt 222,402 (99%)Completion 1,859 (1%)

Daily average tokens per run, last 30 days

Oct 30Total 114,618Prompt 112,338Completion 2,279

Range

Min: 0
p25: 49,706
p50: 106,036
p75: 203,799
p90: 416,606
Max: 4,631,643

Test Claude Sonnet 5 on your store

Start a run to see how Claude Sonnet 5 handles your store’s checkout, call by call.

Start a run