SAI360SAIOS

Model Bench

Head-to-head A/B results per capability — challenger win-rate, cost delta, and 1-click promotion of a winning model.

Challenger recommendations

CapabilityChallenger modelSamplesWin-rateAvg cost deltaRecommendationAction
No benchmark data yet. Enable A/B (Settings → A/B benchmarking) to auto-shadow recently triaged tickets, or run a “force both” on a ticket.

Recent benchmark runs

WhenCapabilityPrimaryChallengerJudgeHumanWinnerCost deltaModeTicket
No benchmark runs recorded yet.