All scorecards
Xyntherium
Perplexity
ActiveLast updated: Jul 29, 2026
Routed for
✓ General reasoning· Documents & images✓ Live URL fetch✓ Deep research
Perplexityis routed to questions that play to these strengths. Where a task needs a capability it doesn’t have, the question goes to the models that do — and Perplexity sits that one out.
Across all tasks
| Metric | 7d | 30d | All-time |
|---|---|---|---|
| Response rate | 100% | 100% | 93% |
| p50 latency | 14.8s | 10.4s | 12.3s |
| p95 latency | 14.8s | 22.4s | 25.4s |
| Avg cost / query | 2.8534¢ | 2.6106¢ | 2.5852¢ |
| Agreement w/ verdict | 100% | 74% | 82% |
| Consensus flip rate | 100% | 89% | 71% |
Routed on 9of the last 30 days’ queries it was eligible for, answering 9.
By task type · 30-day
Score = router weight| Task | Responded | p95 | Agreement | Flip | Score |
|---|---|---|---|---|---|
| General | 100% | 22.4s | 74% | 89% | 0.67 |
The score blends agreement with the verified verdict, response rate, and speed over the last 30 days. When a task has more capable models than a panel needs, the router prefers the higher scores — a soft preference, never a hard exclusion.
Rebuilt daily from live verification traffic. Capability flags are set by hand; the performance numbers are earned.