bradsansnow Claude Opus 4.8 commited on
Commit
ea1199a
·
1 Parent(s): 31200b7

Polish leaderboard cards: clickable titles, tooltips, hover animation

Browse files

- Make EnterpriseOps-Gym and EVA-Bench titles clickable links with
multicolor sweep hover animation (logo colors → settles #006DAA)
- Add accessible tooltips (ARIA + keyboard + reduced-motion) on titles
and metrics
- Rename metric labels: Task Success Rate, EVA-Accuracy, EVA-Experience,
Pass@1
- Update #1 model subtitles: "Mixed Models · Cascade", "Google ·
Speech-to-Speech"
- Switch leaderboard link hover from wasabi-green to #006DAA (WCAG AA)
- Section heading "Benchmark cards" → "Benchmark Leaderboard"

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

Files changed (2) hide show
  1. index.html +48 -14
  2. style.css +101 -0
index.html CHANGED
@@ -148,7 +148,7 @@
148
  <!-- Capability leaders header -->
149
  <div class="flex flex-col md:flex-row md:items-end md:justify-between gap-6 mb-8">
150
  <div>
151
- <h2 class="text-infinite-blue font-bold text-3xl tracking-tight mb-2">Benchmark cards</h2>
152
  <p class="text-on-surface-variant font-light text-[15px]">A high-level overview of each NOWAI-Bench benchmark.</p>
153
  </div>
154
  <div class="md:text-right">
@@ -162,17 +162,29 @@
162
  <div class="bg-white border border-border-subtle rounded-2xl p-8 card-shadow border-l-[4px] accent-infinite">
163
  <div class="flex items-center gap-3 mb-8">
164
  <span class="w-3 h-3 rounded-full fill-infinite"></span>
165
- <h3 class="text-infinite-blue font-bold text-2xl tracking-tight">EnterpriseOps-Gym</h3>
 
 
 
 
 
 
166
  <span class="text-on-surface-variant text-xs font-medium bg-surface-muted px-2 py-0.5 rounded">long-horizon task agents</span>
167
  </div>
168
  <div class="mb-6">
169
  <div class="font-mono text-[10px] text-on-surface-variant uppercase tracking-[0.15em] mb-2">Top model</div>
170
  <div class="text-infinite-blue font-bold text-xl leading-tight">Claude Opus 4.5</div>
171
- <div class="text-on-surface-variant text-sm font-medium">Anthropic · cascade</div>
172
  </div>
173
- <div class="bg-[#f0f9f3] border-l-4 border-wasabi-green rounded-xl p-4 flex items-baseline gap-3 mb-8">
174
  <span class="text-infinite-blue font-bold text-3xl tabular-nums leading-none">37.4<span class="text-on-surface-variant text-lg font-medium ml-0.5">%</span></span>
175
- <span class="font-mono text-[10px] text-on-surface-variant uppercase tracking-wider font-medium">Success rate · Oracle mode</span>
 
 
 
 
 
 
176
  </div>
177
  <div class="space-y-4">
178
  <!-- Runner 2 -->
@@ -204,7 +216,7 @@
204
  </div>
205
  </div>
206
  <div class="mt-8 pt-6 border-t border-border-subtle">
207
- <a class="text-infinite-blue font-bold text-sm hover:text-wasabi-green transition-colors flex items-center gap-2 group" href="https://enterpriseops-gym.github.io/#leaderboard" target="_blank" rel="noopener">
208
  View full EOG leaderboard
209
  <span class="material-symbols-outlined text-sm transition-transform group-hover:translate-x-0.5 group-hover:-translate-y-0.5">arrow_outward</span>
210
  </a>
@@ -214,20 +226,34 @@
214
  <div class="bg-white border border-border-subtle rounded-2xl p-8 card-shadow border-l-[4px] accent-indigo">
215
  <div class="flex items-center gap-3 mb-8">
216
  <span class="w-3 h-3 rounded-full fill-indigo"></span>
217
- <h3 class="text-infinite-blue font-bold text-2xl tracking-tight">EVA-Bench</h3>
 
 
 
 
 
 
218
  <span class="text-on-surface-variant text-xs font-medium bg-surface-muted px-2 py-0.5 rounded">voice agents · accuracy and experience</span>
219
  </div>
220
  <div class="space-y-10">
221
  <!-- Accuracy Split -->
222
  <div>
223
  <div class="flex justify-between items-baseline mb-3">
224
- <span class="font-mono text-[10px] text-[#5240CC] uppercase tracking-[0.15em] font-bold">Accuracy</span>
225
- <span class="font-mono text-[10px] text-on-surface-variant uppercase tracking-wider">EVA-A · PASS@3</span>
 
 
 
 
 
 
 
 
226
  </div>
227
  <div class="bg-[#f2f0ff] border-l-4 border-bright-indigo rounded-lg p-3 flex justify-between items-center mb-4">
228
  <div>
229
  <div class="text-infinite-blue font-bold text-base leading-tight">Nova + GPT-5.4 + Sonic</div>
230
- <div class="text-on-surface-variant text-[11px] font-medium">cascade · mixed</div>
231
  </div>
232
  <span class="text-infinite-blue font-bold text-2xl tabular-nums">0.41</span>
233
  </div>
@@ -253,13 +279,21 @@
253
  <!-- Experience Split -->
254
  <div class="pt-8 border-t border-dashed border-border-subtle">
255
  <div class="flex justify-between items-baseline mb-3">
256
- <span class="font-mono text-[10px] text-[#006DAA] uppercase tracking-[0.15em] font-bold">Experience</span>
257
- <span class="font-mono text-[10px] text-on-surface-variant uppercase tracking-wider">EVA-X · PASS@3</span>
 
 
 
 
 
 
 
 
258
  </div>
259
  <div class="bg-[#f0f9ff] border-l-4 border-bright-blue rounded-lg p-3 flex justify-between items-center mb-4">
260
  <div>
261
  <div class="text-infinite-blue font-bold text-base leading-tight">Gemini Live</div>
262
- <div class="text-on-surface-variant text-[11px] font-medium">Google · S2S</div>
263
  </div>
264
  <span class="text-infinite-blue font-bold text-2xl tabular-nums">0.49</span>
265
  </div>
@@ -284,7 +318,7 @@
284
  </div>
285
  </div>
286
  <div class="mt-8 pt-6 border-t border-border-subtle">
287
- <a class="text-infinite-blue font-bold text-sm hover:text-wasabi-green transition-colors flex items-center gap-2 group" href="https://servicenow.github.io/eva/#results" target="_blank" rel="noopener">
288
  View full EVA leaderboard
289
  <span class="material-symbols-outlined text-sm transition-transform group-hover:translate-x-0.5 group-hover:-translate-y-0.5">arrow_outward</span>
290
  </a>
 
148
  <!-- Capability leaders header -->
149
  <div class="flex flex-col md:flex-row md:items-end md:justify-between gap-6 mb-8">
150
  <div>
151
+ <h2 class="text-infinite-blue font-bold text-3xl tracking-tight mb-2">Benchmark Leaderboard</h2>
152
  <p class="text-on-surface-variant font-light text-[15px]">A high-level overview of each NOWAI-Bench benchmark.</p>
153
  </div>
154
  <div class="md:text-right">
 
162
  <div class="bg-white border border-border-subtle rounded-2xl p-8 card-shadow border-l-[4px] accent-infinite">
163
  <div class="flex items-center gap-3 mb-8">
164
  <span class="w-3 h-3 rounded-full fill-infinite"></span>
165
+ <h3 class="text-2xl tracking-tight"><a class="title-anim font-bold" href="https://enterpriseops-gym.github.io/" target="_blank" rel="noopener">EnterpriseOps-Gym</a></h3>
166
+ <span class="tooltip">
167
+ <button type="button" class="tooltip-trigger" aria-label="About EnterpriseOps-Gym" aria-describedby="tt-eog">
168
+ <span class="material-symbols-outlined" style="font-size:18px" aria-hidden="true">info</span>
169
+ </button>
170
+ <span class="tooltip-bubble" role="tooltip" id="tt-eog">Long-horizon task agents evaluated across eight enterprise domains.</span>
171
+ </span>
172
  <span class="text-on-surface-variant text-xs font-medium bg-surface-muted px-2 py-0.5 rounded">long-horizon task agents</span>
173
  </div>
174
  <div class="mb-6">
175
  <div class="font-mono text-[10px] text-on-surface-variant uppercase tracking-[0.15em] mb-2">Top model</div>
176
  <div class="text-infinite-blue font-bold text-xl leading-tight">Claude Opus 4.5</div>
177
+ <div class="text-on-surface-variant text-sm font-medium">Anthropic</div>
178
  </div>
179
+ <div class="bg-[#f0f9f3] border-l-4 border-wasabi-green rounded-xl p-4 flex items-center gap-3 mb-8">
180
  <span class="text-infinite-blue font-bold text-3xl tabular-nums leading-none">37.4<span class="text-on-surface-variant text-lg font-medium ml-0.5">%</span></span>
181
+ <span class="font-mono text-[10px] text-on-surface-variant uppercase tracking-wider font-medium">Task Success Rate · Oracle mode</span>
182
+ <span class="tooltip">
183
+ <button type="button" class="tooltip-trigger" aria-label="Task Success Rate definition" aria-describedby="tt-eog-metric">
184
+ <span class="material-symbols-outlined" style="font-size:16px" aria-hidden="true">info</span>
185
+ </button>
186
+ <span class="tooltip-bubble" role="tooltip" id="tt-eog-metric">A task passes only if all verification conditions are met.</span>
187
+ </span>
188
  </div>
189
  <div class="space-y-4">
190
  <!-- Runner 2 -->
 
216
  </div>
217
  </div>
218
  <div class="mt-8 pt-6 border-t border-border-subtle">
219
+ <a class="text-infinite-blue font-bold text-sm hover:text-[#006DAA] transition-colors flex items-center gap-2 group" href="https://enterpriseops-gym.github.io/#leaderboard" target="_blank" rel="noopener">
220
  View full EOG leaderboard
221
  <span class="material-symbols-outlined text-sm transition-transform group-hover:translate-x-0.5 group-hover:-translate-y-0.5">arrow_outward</span>
222
  </a>
 
226
  <div class="bg-white border border-border-subtle rounded-2xl p-8 card-shadow border-l-[4px] accent-indigo">
227
  <div class="flex items-center gap-3 mb-8">
228
  <span class="w-3 h-3 rounded-full fill-indigo"></span>
229
+ <h3 class="text-2xl tracking-tight"><a class="title-anim font-bold" href="https://servicenow.github.io/eva/" target="_blank" rel="noopener">EVA-Bench</a></h3>
230
+ <span class="tooltip">
231
+ <button type="button" class="tooltip-trigger" aria-label="About EVA-Bench" aria-describedby="tt-eva">
232
+ <span class="material-symbols-outlined" style="font-size:18px" aria-hidden="true">info</span>
233
+ </button>
234
+ <span class="tooltip-bubble" role="tooltip" id="tt-eva">Voice agents evaluated on task accuracy and conversational experience.</span>
235
+ </span>
236
  <span class="text-on-surface-variant text-xs font-medium bg-surface-muted px-2 py-0.5 rounded">voice agents · accuracy and experience</span>
237
  </div>
238
  <div class="space-y-10">
239
  <!-- Accuracy Split -->
240
  <div>
241
  <div class="flex justify-between items-baseline mb-3">
242
+ <span class="font-mono text-[10px] text-[#5240CC] uppercase tracking-[0.15em] font-bold">EVA-Accuracy</span>
243
+ <span class="flex items-center gap-1">
244
+ <span class="font-mono text-[10px] text-on-surface-variant uppercase tracking-wider">Pass@1</span>
245
+ <span class="tooltip">
246
+ <button type="button" class="tooltip-trigger" aria-label="EVA-Accuracy definition" aria-describedby="tt-eva-acc">
247
+ <span class="material-symbols-outlined" style="font-size:15px" aria-hidden="true">info</span>
248
+ </button>
249
+ <span class="tooltip-bubble" role="tooltip" id="tt-eva-acc">Scores for accuracy. All values normalized to 0–1 (higher is better). 95% bootstrap confidence intervals shown for each value.</span>
250
+ </span>
251
+ </span>
252
  </div>
253
  <div class="bg-[#f2f0ff] border-l-4 border-bright-indigo rounded-lg p-3 flex justify-between items-center mb-4">
254
  <div>
255
  <div class="text-infinite-blue font-bold text-base leading-tight">Nova + GPT-5.4 + Sonic</div>
256
+ <div class="text-on-surface-variant text-[11px] font-medium">Mixed Models · Cascade</div>
257
  </div>
258
  <span class="text-infinite-blue font-bold text-2xl tabular-nums">0.41</span>
259
  </div>
 
279
  <!-- Experience Split -->
280
  <div class="pt-8 border-t border-dashed border-border-subtle">
281
  <div class="flex justify-between items-baseline mb-3">
282
+ <span class="font-mono text-[10px] text-[#006DAA] uppercase tracking-[0.15em] font-bold">EVA-Experience</span>
283
+ <span class="flex items-center gap-1">
284
+ <span class="font-mono text-[10px] text-on-surface-variant uppercase tracking-wider">Pass@1</span>
285
+ <span class="tooltip">
286
+ <button type="button" class="tooltip-trigger" aria-label="EVA-Experience definition" aria-describedby="tt-eva-exp">
287
+ <span class="material-symbols-outlined" style="font-size:15px" aria-hidden="true">info</span>
288
+ </button>
289
+ <span class="tooltip-bubble" role="tooltip" id="tt-eva-exp">Scores for conversational experience. All values normalized to 0–1 (higher is better). 95% bootstrap confidence intervals shown for each value.</span>
290
+ </span>
291
+ </span>
292
  </div>
293
  <div class="bg-[#f0f9ff] border-l-4 border-bright-blue rounded-lg p-3 flex justify-between items-center mb-4">
294
  <div>
295
  <div class="text-infinite-blue font-bold text-base leading-tight">Gemini Live</div>
296
+ <div class="text-on-surface-variant text-[11px] font-medium">Google · Speech-to-Speech</div>
297
  </div>
298
  <span class="text-infinite-blue font-bold text-2xl tabular-nums">0.49</span>
299
  </div>
 
318
  </div>
319
  </div>
320
  <div class="mt-8 pt-6 border-t border-border-subtle">
321
+ <a class="text-infinite-blue font-bold text-sm hover:text-[#006DAA] transition-colors flex items-center gap-2 group" href="https://servicenow.github.io/eva/#results" target="_blank" rel="noopener">
322
  View full EVA leaderboard
323
  <span class="material-symbols-outlined text-sm transition-transform group-hover:translate-x-0.5 group-hover:-translate-y-0.5">arrow_outward</span>
324
  </a>
style.css CHANGED
@@ -73,3 +73,104 @@ body {
73
  opacity: 1;
74
  }
75
  }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73
  opacity: 1;
74
  }
75
  }
76
+
77
+ /* Title hover — rests infinite-blue, sweeps logo colors L→R, settles deep blue.
78
+ Reverses smoothly on mouse-leave. Fires on keyboard focus too. */
79
+ .title-anim {
80
+ background-image: linear-gradient(90deg,
81
+ #032D42 0%, #032D42 30%,
82
+ #7661FF 42%, #63DF4E 52%, #52B8FF 60%,
83
+ #006DAA 70%, #006DAA 100%);
84
+ background-size: 320% 100%;
85
+ background-position: 0 0;
86
+ -webkit-background-clip: text;
87
+ background-clip: text;
88
+ color: transparent;
89
+ -webkit-text-fill-color: transparent;
90
+ transition: background-position 0.5s ease;
91
+ }
92
+ .title-anim:hover,
93
+ .title-anim:focus-visible {
94
+ animation: title-sweep 0.9s ease forwards;
95
+ }
96
+ @keyframes title-sweep {
97
+ from { background-position: 0 0; }
98
+ to { background-position: 100% 0; }
99
+ }
100
+ @media (prefers-reduced-motion: reduce) {
101
+ .title-anim { transition: none; }
102
+ .title-anim:hover,
103
+ .title-anim:focus-visible {
104
+ animation: none;
105
+ color: #006DAA;
106
+ -webkit-text-fill-color: #006DAA;
107
+ }
108
+ }
109
+
110
+ /* Accessible tooltip — shows on hover and keyboard focus */
111
+ .tooltip {
112
+ position: relative;
113
+ display: inline-flex;
114
+ align-items: center;
115
+ }
116
+ .tooltip-trigger {
117
+ display: inline-flex;
118
+ align-items: center;
119
+ justify-content: center;
120
+ padding: 0;
121
+ border: 0;
122
+ background: none;
123
+ color: #5b6b75;
124
+ cursor: help;
125
+ line-height: 0;
126
+ border-radius: 9999px;
127
+ transition: color 0.15s ease;
128
+ }
129
+ .tooltip-trigger:hover,
130
+ .tooltip:focus-within .tooltip-trigger {
131
+ color: #032D42;
132
+ }
133
+ .tooltip-trigger:focus-visible {
134
+ outline: 2px solid #7661FF;
135
+ outline-offset: 2px;
136
+ }
137
+ .tooltip-bubble {
138
+ position: absolute;
139
+ bottom: calc(100% + 8px);
140
+ left: 50%;
141
+ transform: translateX(-50%);
142
+ z-index: 30;
143
+ width: max-content;
144
+ max-width: 240px;
145
+ padding: 8px 10px;
146
+ border-radius: 8px;
147
+ background: #032D42;
148
+ color: #ffffff;
149
+ font-size: 12px;
150
+ font-weight: 400;
151
+ line-height: 1.45;
152
+ text-transform: none;
153
+ letter-spacing: normal;
154
+ box-shadow: 0 6px 16px rgba(3, 45, 66, 0.18);
155
+ opacity: 0;
156
+ visibility: hidden;
157
+ pointer-events: none;
158
+ transition: opacity 0.15s ease;
159
+ }
160
+ .tooltip-bubble::after {
161
+ content: "";
162
+ position: absolute;
163
+ top: 100%;
164
+ left: 50%;
165
+ transform: translateX(-50%);
166
+ border: 5px solid transparent;
167
+ border-top-color: #032D42;
168
+ }
169
+ .tooltip:hover .tooltip-bubble,
170
+ .tooltip:focus-within .tooltip-bubble {
171
+ opacity: 1;
172
+ visibility: visible;
173
+ }
174
+ @media (prefers-reduced-motion: reduce) {
175
+ .tooltip-bubble { transition: none; }
176
+ }