OpenAIo4-mini (Reasoning)
OpenAI's compact reasoning model. Currently non-functional for shopping — 92.9% tool error rate with almost every tool call failing. Appears to struggle with MCP tool schemas entirely. Not recommended until OpenAI addresses the tool-use reliability issues.
- Avg tokens per run
- 69,472
- Avg duration
- 39.0s
- Turns to checkout
- 11.5
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%8.9%
- Cart rate20%29.3%
- Search rate10%78.9%
- Turn efficiency15%6%
- Token efficiency15%17%
21.1% of runs failed with errors.
Top stores
Development stores are hidden.
| Store | Checkout | Cart |
|---|---|---|
| store hidden | 66.7% | 66.7% |
| everlane.com | 60% | 60% |
| store hidden | 33.3% | 33.3% |
| saltwarp.shop | 0% | 0% |
| store hidden | 0% | 0% |
| store hidden | 0% | 0% |
| craze.wtf | 0% | 0% |
| goswingofficial.com | 0% | 50% |
| store hidden | 0% | 0% |
| teveo.com | 0% | 50% |
Known issues
- HighNon-Functional
92.9% tool error rate — almost every tool call fails.
- HighSchema Incompatibility
Cannot correctly format MCP tool arguments. Not usable for shopping agent tasks.
Token usage
- Avg per run
- 69,472
- Average of all models
- 78,176
- Against the average
- −11%
- Median (p50)
- 29,827
- p90
- 148,773
Prompt and completion
Daily average tokens per run, last 30 days
Oct 16Total 10,976Prompt 10,511Completion 465
Range
- Min
- 0
- p25
- 15,535
- p50
- 29,827
- p75
- 77,163
- p90
- 148,773
- Max
- 721,744
Test o4-mini (Reasoning) on your store
Start a run to see how o4-mini (Reasoning) handles your store’s checkout, call by call.
Compare with other models
Rates are checkout rates. Full comparison view