Google

Gemini 2.5 Pro

Google's previous-gen flagship. Highest failure rate among Google models (16%) with a near-10% tool error rate. When it succeeds, checkout takes 8.5 turns on average. Being superseded by Gemini 3.1 Pro which outperforms it on every metric.

Avg tokens per run: 50,062
Avg duration: 37.8s
Turns to checkout: 9

Start a run with Gemini 2.5 Pro Compare

Shopping score

34/100Weak

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%19.5%
Cart rate20%38.6%
Search rate10%68.9%
Turn efficiency15%38%
Token efficiency15%41%

30.7% of runs failed with errors.

Top stores

Development stores are hidden.

Store	Checkout	Cart
store hidden	75%	75%
pier1.com	66.7%	66.7%
ucp.travel	58.3%	58.3%
roxy.com	50%	50%
store hidden	50%	66.7%
store hidden	50%	100%
store hidden	50%	50%
houseofparfum.nl	31.3%	37.5%
store hidden	20%	70%
allbirds.com	20%	20%

Known issues

HighHigh Failure Rate
16% of runs fail — highest among Google models. Primarily timeout and connection issues.
MediumTool Error Rate
9.9% error rate on tool calls.

Token usage

Avg per run: 50,062
Average of all models: 78,415
Against the average: −36%
Median (p50): 30,385
p90: 110,748

Prompt and completion

Prompt 48,025 (96%)Completion 2,037 (4%)

Daily average tokens per run, last 30 days

Oct 21Total 33,332Prompt 32,891Completion 441

Range

Min: 0
p25: 12,928
p50: 30,385
p75: 66,581
p90: 110,748
Max: 442,998

Test Gemini 2.5 Pro on your store

Start a run to see how Gemini 2.5 Pro handles your store’s checkout, call by call.

Start a run