Xyntherium
Model Scorecards
A permanent record of how each model performs on the panel — how often it answers, how fast, how closely it tracks the verified consensus, and where it’s strongest. Every number is earned on live verification traffic.
Last updated: Jun 10, 2026
ClaudeActive
- Responded
- 100%
- p95
- 9.1s
- Agreement
- 53%
GPTActive
- Responded
- 100%
- p95
- 6.9s
- Agreement
- 82%
GrokActive
- Responded
- 100%
- p95
- 8.7s
- Agreement
- 64%
PerplexityActive
- Responded
- 75%
- p95
- 4.3s
- Agreement
- 75%
GeminiActive
- Responded
- 75%
- p95
- 6.4s
- Agreement
- 44%
DeepSeekActive
- Responded
- 100%
- p95
- 18.2s
- Agreement
- 78%
KimiBenched
Gathering data — the first numbers appear after the next daily refresh.
View scorecard →Scorecards are rebuilt daily from live verification traffic. The same per-task scores shown here are what the router weighs when it has more capable models than a panel needs — so the strongest model for a task is the one most likely to answer it.
