Skip to content

Benchmark

ServiceNow EVA-Bench · Voice Agent Accuracy

Scores are percentages. Higher is better.

Models measured
1
Scores recorded
1
Sources
1
IQ weight
No weight published

Score distribution

74%
Mean
74%
Median
0%
Std dev
74%
10th percentile
74%
90th percentile
74%
Min

Leaderboard

#ModelScore
1Grok Voice 3.0SpaceXAI release · ServiceNow EVA-Bench · 200+ enterprise scenarios· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.74%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.