xAIGrok 4.3 Retired
This model is no longer available to run. Its stats below reflect past runs and are kept for reference.
xAI's Grok 4.3 (this slot also carries earlier Grok 4 runs). Standout reliability in our benchmark — near-zero session failures and a very low tool error rate — with an efficient checkout path; latency was the main drawback, the slowest of the frontier models. Retired: superseded by Grok 4.5.
- Avg tokens per run
- 35,601
- Avg duration
- 45.4s
- Turns to checkout
- 6.5
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%26.3%
- Cart rate20%33.1%
- Search rate10%64.4%
- Turn efficiency15%69%
- Token efficiency15%61%
35.6% of runs failed with errors.
Top stores
Development stores are hidden.
| Store | Checkout | Cart |
|---|---|---|
| store hidden | 100% | 100% |
| ucp.travel | 100% | 100% |
| store hidden | 80% | 100% |
| store hidden | 50% | 100% |
| houseofparfum.nl | 46.4% | 50% |
| everlane.com | 33.3% | 33.3% |
| allbirds.com | 0% | 0% |
| store hidden | 0% | 0% |
| store hidden | 0% | 0% |
| store hidden | 0% | 0% |
Known issues
- MediumHigh Latency
84 seconds average per run — slowest frontier model by a significant margin.
Token usage
- Avg per run
- 35,601
- Average of all models
- 77,769
- Against the average
- −54%
- Median (p50)
- 22,188
- p90
- 93,360
Prompt and completion
Daily average tokens per run, last 30 days
No daily trend data yet. Start more runs to see token usage over time.
Range
- Min
- 0
- p25
- 9,814
- p50
- 22,188
- p75
- 42,505
- p90
- 93,360
- Max
- 401,007
Test Grok 4.3 on your store
Start a run to see how Grok 4.3 handles your store’s checkout, call by call.
Compare with other models
Rates are checkout rates. Full comparison view