Spaces:
Running
Running
Update index.html
Browse files- index.html +223 -26
index.html
CHANGED
@@ -4,46 +4,243 @@
|
|
4 |
<meta charset="UTF-8">
|
5 |
<title>Model Benchmark: First Grade Math</title>
|
6 |
<style>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
body {
|
8 |
-
font-family:
|
9 |
-
background:
|
10 |
margin: 0;
|
11 |
-
padding:
|
12 |
-
text-
|
|
|
13 |
}
|
14 |
-
|
15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
img {
|
18 |
-
max-width:
|
19 |
height: auto;
|
20 |
-
border:
|
21 |
-
box-shadow:
|
22 |
}
|
|
|
23 |
.model-info {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
margin-top: 20px;
|
25 |
-
font-size: 16px;
|
26 |
}
|
27 |
-
|
28 |
-
|
29 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
}
|
31 |
-
|
32 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
}
|
34 |
</style>
|
35 |
</head>
|
36 |
<body>
|
37 |
-
<
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
<
|
45 |
-
<
|
46 |
-
</
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
</div>
|
48 |
</body>
|
49 |
-
</html>
|
|
|
4 |
<meta charset="UTF-8">
|
5 |
<title>Model Benchmark: First Grade Math</title>
|
6 |
<style>
|
7 |
+
:root {
|
8 |
+
--primary: #4a6fa5;
|
9 |
+
--secondary: #6b8cbe;
|
10 |
+
--accent: #ff6b6b;
|
11 |
+
--background: #f5f7fa;
|
12 |
+
--card-bg: #ffffff;
|
13 |
+
--text-dark: #2d3748;
|
14 |
+
--text-light: #4a5568;
|
15 |
+
--success: #48bb78;
|
16 |
+
--error: #e53e3e;
|
17 |
+
}
|
18 |
+
|
19 |
body {
|
20 |
+
font-family: 'Segoe UI', Roboto, -apple-system, BlinkMacSystemFont, sans-serif;
|
21 |
+
background: var(--background);
|
22 |
margin: 0;
|
23 |
+
padding: 0;
|
24 |
+
color: var(--text-dark);
|
25 |
+
line-height: 1.6;
|
26 |
}
|
27 |
+
|
28 |
+
.container {
|
29 |
+
max-width: 1000px;
|
30 |
+
margin: 0 auto;
|
31 |
+
padding: 40px 20px;
|
32 |
+
}
|
33 |
+
|
34 |
+
header {
|
35 |
+
background: linear-gradient(135deg, var(--primary), var(--secondary));
|
36 |
+
color: white;
|
37 |
+
padding: 30px 0;
|
38 |
+
border-radius: 12px;
|
39 |
+
margin-bottom: 30px;
|
40 |
+
box-shadow: 0 4px 12px rgba(0,0,0,0.1);
|
41 |
+
}
|
42 |
+
|
43 |
+
h1 {
|
44 |
+
margin: 0;
|
45 |
+
font-size: 2.4rem;
|
46 |
+
font-weight: 700;
|
47 |
}
|
48 |
+
|
49 |
+
h2 {
|
50 |
+
color: var(--primary);
|
51 |
+
font-size: 1.8rem;
|
52 |
+
margin-top: 40px;
|
53 |
+
margin-bottom: 20px;
|
54 |
+
position: relative;
|
55 |
+
padding-bottom: 10px;
|
56 |
+
}
|
57 |
+
|
58 |
+
h2::after {
|
59 |
+
content: '';
|
60 |
+
position: absolute;
|
61 |
+
bottom: 0;
|
62 |
+
left: 0;
|
63 |
+
width: 60px;
|
64 |
+
height: 4px;
|
65 |
+
background: var(--accent);
|
66 |
+
border-radius: 2px;
|
67 |
+
}
|
68 |
+
|
69 |
+
.chart-container {
|
70 |
+
background: var(--card-bg);
|
71 |
+
border-radius: 12px;
|
72 |
+
padding: 30px;
|
73 |
+
box-shadow: 0 8px 20px rgba(0,0,0,0.06);
|
74 |
+
margin: 30px 0;
|
75 |
+
}
|
76 |
+
|
77 |
img {
|
78 |
+
max-width: 100%;
|
79 |
height: auto;
|
80 |
+
border-radius: 8px;
|
81 |
+
box-shadow: 0 4px 12px rgba(0,0,0,0.08);
|
82 |
}
|
83 |
+
|
84 |
.model-info {
|
85 |
+
background: var(--card-bg);
|
86 |
+
border-radius: 12px;
|
87 |
+
padding: 30px;
|
88 |
+
box-shadow: 0 8px 20px rgba(0,0,0,0.06);
|
89 |
+
}
|
90 |
+
|
91 |
+
.model-cards {
|
92 |
+
display: flex;
|
93 |
+
flex-wrap: wrap;
|
94 |
+
gap: 20px;
|
95 |
+
justify-content: center;
|
96 |
margin-top: 20px;
|
|
|
97 |
}
|
98 |
+
|
99 |
+
.model-card {
|
100 |
+
background: var(--card-bg);
|
101 |
+
border-radius: 10px;
|
102 |
+
padding: 20px;
|
103 |
+
box-shadow: 0 4px 10px rgba(0,0,0,0.05);
|
104 |
+
border-left: 5px solid var(--primary);
|
105 |
+
width: calc(33% - 20px);
|
106 |
+
min-width: 250px;
|
107 |
+
transition: transform 0.2s, box-shadow 0.2s;
|
108 |
}
|
109 |
+
|
110 |
+
.model-card:hover {
|
111 |
+
transform: translateY(-5px);
|
112 |
+
box-shadow: 0 8px 15px rgba(0,0,0,0.1);
|
113 |
+
}
|
114 |
+
|
115 |
+
.model-name {
|
116 |
+
font-weight: 700;
|
117 |
+
font-size: 1.2rem;
|
118 |
+
color: var(--primary);
|
119 |
+
margin-bottom: 10px;
|
120 |
+
}
|
121 |
+
|
122 |
+
.stats {
|
123 |
+
display: flex;
|
124 |
+
justify-content: space-between;
|
125 |
+
margin-top: 15px;
|
126 |
+
}
|
127 |
+
|
128 |
+
.stat {
|
129 |
+
text-align: center;
|
130 |
+
flex: 1;
|
131 |
+
}
|
132 |
+
|
133 |
+
.stat-value {
|
134 |
+
font-size: 1.5rem;
|
135 |
+
font-weight: 700;
|
136 |
+
}
|
137 |
+
|
138 |
+
.correct {
|
139 |
+
color: var(--success);
|
140 |
+
}
|
141 |
+
|
142 |
+
.incorrect {
|
143 |
+
color: var(--error);
|
144 |
+
}
|
145 |
+
|
146 |
+
.stat-label {
|
147 |
+
font-size: 0.85rem;
|
148 |
+
color: var(--text-light);
|
149 |
+
}
|
150 |
+
|
151 |
+
.accuracy-bar {
|
152 |
+
height: 8px;
|
153 |
+
background: #f0f0f0;
|
154 |
+
border-radius: 4px;
|
155 |
+
margin-top: 10px;
|
156 |
+
overflow: hidden;
|
157 |
+
}
|
158 |
+
|
159 |
+
.accuracy-fill {
|
160 |
+
height: 100%;
|
161 |
+
background: var(--primary);
|
162 |
+
border-radius: 4px;
|
163 |
+
}
|
164 |
+
|
165 |
+
footer {
|
166 |
+
margin-top: 40px;
|
167 |
+
text-align: center;
|
168 |
+
color: var(--text-light);
|
169 |
+
font-size: 0.9rem;
|
170 |
}
|
171 |
</style>
|
172 |
</head>
|
173 |
<body>
|
174 |
+
<div class="container">
|
175 |
+
<header>
|
176 |
+
<h1>Model Benchmark: First Grade Math</h1>
|
177 |
+
<p>Performance comparison across 1,000 questions per model</p>
|
178 |
+
</header>
|
179 |
+
|
180 |
+
<div class="chart-container">
|
181 |
+
<h2>Performance Overview</h2>
|
182 |
+
<img src="download.png" alt="Model Benchmark Chart">
|
183 |
+
</div>
|
184 |
+
|
185 |
+
<div class="model-info">
|
186 |
+
<h2>Models Benchmarked</h2>
|
187 |
+
<div class="model-cards">
|
188 |
+
<div class="model-card">
|
189 |
+
<div class="model-name">FlameF0X/MathGPT2</div>
|
190 |
+
<div class="stats">
|
191 |
+
<div class="stat">
|
192 |
+
<div class="stat-value correct">763</div>
|
193 |
+
<div class="stat-label">Correct</div>
|
194 |
+
</div>
|
195 |
+
<div class="stat">
|
196 |
+
<div class="stat-value incorrect">237</div>
|
197 |
+
<div class="stat-label">Incorrect</div>
|
198 |
+
</div>
|
199 |
+
</div>
|
200 |
+
<div class="accuracy-bar">
|
201 |
+
<div class="accuracy-fill" style="width: 76.3%"></div>
|
202 |
+
</div>
|
203 |
+
</div>
|
204 |
+
|
205 |
+
<div class="model-card">
|
206 |
+
<div class="model-name">FlameF0X/Muffin-2.9b-1C25</div>
|
207 |
+
<div class="stats">
|
208 |
+
<div class="stat">
|
209 |
+
<div class="stat-value correct">9</div>
|
210 |
+
<div class="stat-label">Correct</div>
|
211 |
+
</div>
|
212 |
+
<div class="stat">
|
213 |
+
<div class="stat-value incorrect">991</div>
|
214 |
+
<div class="stat-label">Incorrect</div>
|
215 |
+
</div>
|
216 |
+
</div>
|
217 |
+
<div class="accuracy-bar">
|
218 |
+
<div class="accuracy-fill" style="width: 0.9%"></div>
|
219 |
+
</div>
|
220 |
+
</div>
|
221 |
+
|
222 |
+
<div class="model-card">
|
223 |
+
<div class="model-name">FlameF0X/MuffinFace-2</div>
|
224 |
+
<div class="stats">
|
225 |
+
<div class="stat">
|
226 |
+
<div class="stat-value correct">8</div>
|
227 |
+
<div class="stat-label">Correct</div>
|
228 |
+
</div>
|
229 |
+
<div class="stat">
|
230 |
+
<div class="stat-value incorrect">992</div>
|
231 |
+
<div class="stat-label">Incorrect</div>
|
232 |
+
</div>
|
233 |
+
</div>
|
234 |
+
<div class="accuracy-bar">
|
235 |
+
<div class="accuracy-fill" style="width: 0.8%"></div>
|
236 |
+
</div>
|
237 |
+
</div>
|
238 |
+
</div>
|
239 |
+
</div>
|
240 |
+
|
241 |
+
<footer>
|
242 |
+
<p>Benchmark results as of April 2025</p>
|
243 |
+
</footer>
|
244 |
</div>
|
245 |
</body>
|
246 |
+
</html>
|