Compare
A · run_260a81vsB · run_882d52invoice-extractorSwap A and B- Duration
- 12.5s +95%
- A: 6.4s
- Cost
- $0.103 +318%
- A: $0.025
- Tokens
- 23.1k +160%
- A: 8.9k
- Steps
- 9 -18%
- A: 11
- Model changed
- Claude Sonnet
- A: Gemini 2.5 Pro
Steps, aligned
| Change | Step | A | B |
|---|---|---|---|
| Slower | Input policy check | 0.1s | 0.2s |
| Slower | Plan the task | 0.8s | 2.1s |
| Same | validate_totals | 0.4s | 0.7s |
| Slower | Retrieve context · top 8 | 0.3s | 1.1s |
| Slower | Decide next step | 0.9s | 2.1s |
| Slower | ocr_pages | 0.3s | 0.7s |
| Slower | validate_totals | 0.4s | 1.0s |
| Slower | Decide next step | 1.1s | 2.1s |
| Changed | Write final answer | 0.3s | 1.9s |
| Removed | ocr_pages | 0.3s | — |
| Removed | Write final answer | 1.1s | — |
Output diff
− 0 words + 0 words 100% unchangedINV-2026-0412 from Maderera Sur. Total $184,320.00 with 21% VAT, due Oct 31, 2026. Line 7 did not match the PO and was sent for manual review. Posted to the ERP as a draft, held until review.