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
1,364 ms p50, 3,576 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 | 1,268 ms 44,229 in / 1,742 out | 1,630 ms 44,229 in / 1,742 out | 610 ms 42,460 in / 1,463 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 | 2,378 ms 101,196 in / 5,111 out | 1,677 ms 101,196 in / 5,111 out | 641 ms 97,148 in / 4,293 out | -1,036 ms (-62%) | Evaluated | View details |
| 23 | Equivalent | Met | 97% | 2 | 3,885 ms 216,723 in / 8,935 out | 1,214 ms 216,723 in / 8,935 out | 672 ms 208,054 in / 7,505 out | -542 ms (-45%) | Evaluated | View details |
| 24 | Equivalent | Met | 97% | 1 | 1,487 ms 39,806 in / 1,832 out | 1,261 ms 39,806 in / 1,832 out | 703 ms 38,214 in / 1,539 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 | 1,546 ms 60,859 in / 2,573 out | 1,308 ms 60,859 in / 2,573 out | 734 ms 58,425 in / 2,161 out | -574 ms (-44%) | Evaluated | View details |
| 26 | Equivalent | Met | 97% | 1 | 2,817 ms 114,996 in / 4,298 out | 1,355 ms 114,996 in / 4,298 out | 765 ms 110,396 in / 3,610 out | -590 ms (-44%) | Evaluated | View details |
| 27 | Equivalent | Met | 97% | 1 | 635 ms 25,476 in / 1,099 out | 1,402 ms 25,476 in / 1,099 out | 536 ms 24,457 in / 923 out | -866 ms (-62%) | Evaluated | View details |
| 28 | Equivalent | Met | 97% | 1 | 4,652 ms 194,608 in / 9,382 out | 1,449 ms 194,608 in / 9,382 out | 567 ms 186,824 in / 7,881 out | -882 ms (-61%) | Evaluated | View details |
| 29 | Equivalent | Met | 97% | 1 | 1,875 ms 69,351 in / 2,716 out | 1,496 ms 69,351 in / 2,716 out | 598 ms 66,577 in / 2,281 out | -898 ms (-60%) | Evaluated | View details |
| 30 | Equivalent | Met | 97% | 1 | 781 ms 22,822 in / 1,153 out | 1,543 ms 22,822 in / 1,153 out | 629 ms 21,909 in / 969 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.