Verdict
Quality matched on 100% of cases and the candidate is cheaper. Latency is informational during calibration.
Cases evaluated
Evaluation complete
Quality matches
100%
Est. monthly savings
Projected from matching events observed over 30 days
Status
The experiment finished and its verdict is available.
Controlled replay compares both models from the same worker. Production latency is shown separately as context and is not subtracted from candidate replay latency.
claude-sonnet-4-6 and claude-haiku-4-5 received the same frozen prompts in alternating order.
Replayed source p50
1,419 ms
claude-sonnet-4-6
Replayed candidate p50
626 ms
claude-haiku-4-5
Paired median delta
-762 ms (-55%)
95% interval: -874 ms to -690 ms
Controlled p90
1,624 ms / 735 ms
Source / candidate
Production source context
1,027 ms p50, 2,905 ms p90
30 captured measurements from the user's environment
Controlled coverage
30 successful pairs
Only complete source/candidate pairs enter the comparison (provider-completion-v1)
The evaluation compares structured content canonically and reports presentation adherence as separate evidence unless strict formatting is enabled for the feature.
This run's encrypted evidence expires at the date shown above, 14 days after the run was created. The verdict summary and savings estimate remain in experiment history after that run-specific evidence is deleted.
Review the case results before opening sensitive prompt and response evidence. Opening a case is audited.
| Case | Result | Format | Evaluation confidence | Attempts | Production source | Replayed source | Candidate | Replay delta | Status | Case details |
|---|---|---|---|---|---|---|---|---|---|---|
| 21 | Equivalent | Met | 97% | 1 | 5,611 ms 207,877 in / 9,605 out | 1,630 ms 207,877 in / 9,605 out | 610 ms 199,562 in / 8,068 out | -1,020 ms (-63%) | Evaluated |
Replay failures
0 source, 0 candidate
Failures are excluded from percentiles and retained as reliability evidence
| View details |
| 22 | Equivalent | Met | 97% | 1 | 967 ms 59,444 in / 3,074 out | 1,677 ms 59,444 in / 3,074 out | 641 ms 57,066 in / 2,582 out | -1,036 ms (-62%) | Evaluated | View details |
| 23 | Equivalent | Met | 97% | 2 | 790 ms 25,476 in / 1,153 out | 1,214 ms 25,476 in / 1,153 out | 672 ms 24,457 in / 969 out | -542 ms (-45%) | Evaluated | View details |
| 24 | Equivalent | Met | 97% | 1 | 108 ms 21,230 in / 965 out | 1,261 ms 21,230 in / 965 out | 703 ms 20,381 in / 811 out | -558 ms (-44%) | Evaluated | Hide details |
Case 24 evidenceFull captured evidence for this scored comparison. EquivalentFormat metscored97% evaluation confidenceJudge: gemini-3.1-pro-preview Evaluation notesThe candidate preserved the original answer's policy, resolution, and customer-safe guidance. Format evidenceThe response preserved the expected support-answer structure. Captured prompt | ||||||||||
| 25 | Equivalent | Met | 97% | 1 | 3,441 ms 203,454 in / 8,712 out | 1,308 ms 203,454 in / 8,712 out | 734 ms 195,316 in / 7,318 out | -574 ms (-44%) | Evaluated | View details |
| 26 | Equivalent | Met | 97% | 1 | 2,286 ms 58,029 in / 2,788 out | 1,355 ms 58,029 in / 2,788 out | 765 ms 55,708 in / 2,342 out | -590 ms (-44%) | Evaluated | View details |
| 27 | Equivalent | Met | 97% | 1 | 377 ms 24,945 in / 1,045 out | 1,402 ms 24,945 in / 1,045 out | 536 ms 23,947 in / 878 out | -866 ms (-62%) | Evaluated | View details |
| 28 | Equivalent | Met | 97% | 1 | 873 ms 40,691 in / 1,832 out | 1,449 ms 40,691 in / 1,832 out | 567 ms 39,063 in / 1,539 out | -882 ms (-61%) | Evaluated | View details |
| 29 | Equivalent | Met | 97% | 1 | 1,356 ms 56,613 in / 3,145 out | 1,496 ms 56,613 in / 3,145 out | 598 ms 54,348 in / 2,642 out | -898 ms (-60%) | Evaluated | View details |
| 30 | Equivalent | Met | 97% | 1 | 963 ms 24,414 in / 1,179 out | 1,543 ms 24,414 in / 1,179 out | 629 ms 23,437 in / 990 out | -914 ms (-59%) | Evaluated | View details |
Northstar support case 24: resolve the ticket-summary request with the account policy and cited help-center context.
claude-sonnet-4-6
Resolved ticket-summary case 24 with the correct policy, next step, and customer-safe explanation.
claude-haiku-4-5
Cheaper candidate preserved the policy, action, and explanation for ticket-summary case 24.