UCP Playground
Start a run
GoogleGoogle

Gemini 3.1 Pro

Google's latest flagship. Efficient checkout path averaging 6.7 turns with a moderate error rate. Solid all-rounder that handles both Shopify and non-Shopify stores competently. Higher failure rate (10%) than Claude models, primarily from timeout and connection issues rather than schema errors.

Avg tokens per run
63,671
Avg duration
42.8s
Turns to checkout
8
Start a run with Gemini 3.1 ProCompare
Checkout19Cart38.4Search74.9Turn efficiency50Token efficiency0
Shopping score
30/100Weak

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%
  • Cart rate20%38.4%
  • Search rate10%74.9%
  • Turn efficiency15%50%
  • Token efficiency15%0%

24.7% of runs failed with errors.

Top stores

Development stores are hidden.

Store Checkout Cart
store hidden100% 100%
www.jdsports.com.sg100% 100%
kyliecosmetics.com100% 100%
store hidden62.5% 62.5%
www.allbirds.com50% 50%
ucp.travel50% 50%
store hidden50% 100%
houseofparfum.nl47.8% 52.2%
store hidden33.3% 33.3%
forever21.com33.3% 33.3%

Known issues

  • MediumTimeout Failures

    10% failure rate, primarily from timeout and connection errors rather than schema issues.

Token usage

Avg per run
63,671
Average of all models
77,796
Against the average
−18%
Median (p50)
30,689
p90
143,030

Prompt and completion

Prompt 61,573 (97%)Completion 1,799 (3%)

Daily average tokens per run, last 30 days

Oct 29Total 47,305Prompt 46,675Completion 630

Range

Min
0
p25
11,866
p50
30,689
p75
68,149
p90
143,030
Max
1,731,915

Test Gemini 3.1 Pro on your store

Start a run to see how Gemini 3.1 Pro handles your store’s checkout, call by call.

Start a run

Compare with other models

Qwen 3.8 Flash 47.1%Llama 3.3 70B 39.3%Gemini 3.5 Flash 37.8%Claude Sonnet 4.6 34.6%Grok 4.3 26.3%Gemini 2.5 Flash 22.5%Claude Opus 4.8 22.3%DeepSeek V3.2 20.4%DeepSeek V4.1 Flash 20%Gemini 2.5 Pro 19.5%GPT-4o 14.7%Grok 3 Mini (Reasoning) 11.1%Claude Sonnet 5 10.8%GPT-5.5 10.4%Claude Opus 5 9%o4-mini (Reasoning) 8.9%Grok 4.5 7.5%DeepSeek V4 Pro 7.5%DeepSeek V4 Flash 7%Gemini 3.8 Flash 5.6%Gemini 3.6 Flash 5.1%Qwen 3.7 Max 4.8%DeepSeek R1 (Reasoning) 3.4%Kimi K3 3%Llama 4 Maverick 2.2%Gemini 3.7 Flash 0%GPT-6 Luna 0%Muse Spark 1.3 0%QwQ 32B (Reasoning) 0%All models

Rates are checkout rates. Full comparison view