Hugging Face's logo

Spaces:
ServiceNow-AI
/
NowAI-Bench
Running

App Files Community
bradsansnow commited on
Commit
93f60f8
路
1 Parent(s): 9d052fd

Sync leaderboard: EOG + EVA 2026-06-30

Browse files

evaAccuracy:
old: Scribe v2.2 Realtime + GPT-5.4 + Eleven Flash v2 (ElevenAgents)=0.67, Grok Voice Think Fast 1.0=0.59, Nova 3 + GPT-5.4 + Sonic 3=0.5
new: Scribe v2.2 Realtime + GPT-5.4 + Eleven Flash v2 (ElevenAgents)=0.67, Universal 3.5 Pro + GPT-5.4 + Sonic 3.5=0.6, Grok Voice Think Fast 1.0=0.59

Files changed (1) hide show
  1. data/leaderboard.json +14 -14
data/leaderboard.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
- "updated": "2026-06-10T18:19:04.013Z",
3
  "sources": {
4
  "eog": {
5
  "url": "https://raw.githubusercontent.com/EnterpriseOps-Gym/EnterpriseOps-Gym.github.io/main/script.js",
6
- "hash": "sha256:f96e11145e82ffd4bb2654a9e7cf42f5ebd3b10f481aa1027be22a0d3a1badba",
7
- "fetchedAt": "2026-06-10T18:19:04.012Z"
8
  },
9
  "eva": {
10
  "url": "https://raw.githubusercontent.com/ServiceNow/eva/main/website/src/data/leaderboardStats.json",
11
- "hash": "sha256:1f7a33021ffea8a3719c24cf31f75cfeff4b0271f77ef8abfd0063099081b288",
12
- "fetchedAt": "2026-06-10T18:19:04.013Z"
13
  }
14
  },
15
  "eog": {
@@ -71,21 +71,21 @@
71
  },
72
  {
73
  "rank": 2,
 
 
 
 
 
 
 
 
 
74
  "name": "Grok Voice Think Fast 1.0",
75
  "subtitle": "Grok 路 Speech-to-Speech",
76
  "score": 0.59,
77
  "ciLower": 0.54,
78
  "ciUpper": 0.64,
79
  "bar": 59
80
- },
81
- {
82
- "rank": 3,
83
- "name": "Nova 3 + GPT-5.4 + Sonic 3",
84
- "subtitle": "Mixed Models 路 Cascade",
85
- "score": 0.5,
86
- "ciLower": 0.46,
87
- "ciUpper": 0.54,
88
- "bar": 50
89
  }
90
  ]
91
  },
 
1
  {
2
+ "updated": "2026-06-30T19:53:00.268Z",
3
  "sources": {
4
  "eog": {
5
  "url": "https://raw.githubusercontent.com/EnterpriseOps-Gym/EnterpriseOps-Gym.github.io/main/script.js",
6
+ "hash": "sha256:d59657add350403c147709b4a2a86faf89032672fc047020f258fc21a77347d6",
7
+ "fetchedAt": "2026-06-30T19:53:00.267Z"
8
  },
9
  "eva": {
10
  "url": "https://raw.githubusercontent.com/ServiceNow/eva/main/website/src/data/leaderboardStats.json",
11
+ "hash": "sha256:e71bd9e18c294322e706ebc9ca8ac477be01c8caf5d9c25b3121566753f35b77",
12
+ "fetchedAt": "2026-06-30T19:53:00.268Z"
13
  }
14
  },
15
  "eog": {
 
71
  },
72
  {
73
  "rank": 2,
74
+ "name": "Universal 3.5 Pro + GPT-5.4 + Sonic 3.5",
75
+ "subtitle": "Mixed Models 路 Cascade",
76
+ "score": 0.6,
77
+ "ciLower": 0.55,
78
+ "ciUpper": 0.65,
79
+ "bar": 60
80
+ },
81
+ {
82
+ "rank": 3,
83
  "name": "Grok Voice Think Fast 1.0",
84
  "subtitle": "Grok 路 Speech-to-Speech",
85
  "score": 0.59,
86
  "ciLower": 0.54,
87
  "ciUpper": 0.64,
88
  "bar": 59
 
 
 
 
 
 
 
 
 
89
  }
90
  ]
91
  },