Model comparison
Two to four models, side by side on the five measurements behind the shopping score.
Select models
2 of 4 selected| Measurement | Gemini 3.1 Pro | Claude Sonnet 4.6 |
|---|---|---|
| Checkout rate40% of score | 19.9% | 34.3% |
| Cart rate20% of score | 39.1% | 47.7% |
| Search rate10% of score | 75.2% | 80.1% |
| Turn efficiency15% of score | 53/100 | 43/100 |
| Token efficiency15% of score | 0/100 | 0/100 |
| Avg tokensper run · not in the score | 64,130 | 72,758 |
| Avg durationper run · not in the score | 42.8s | 33.9s |
Best of the selection
Checkout rateClaude Sonnet 4.634.3%
Cart rateClaude Sonnet 4.647.7%
Search rateClaude Sonnet 4.680.1%
Turn efficiencyGemini 3.1 Pro53/100
Token efficiencyNo model reached this stage
These rates are averages across every store in our runs. Yours will differ: the same model scores differently against a strict store and an unenforced one.
Start a run