Spaces:
Running
Running
Your Name commited on
Commit ยท
ad59b21
1
Parent(s): ab0bf39
update new leaderboard
Browse files- .DS_Store +0 -0
- app.py +0 -0
- assets/model_color.json +55 -28
- gallery_tab.py +284 -284
- leaderboard_utils.py +6 -0
- rank_data_03_25_2025.json +263 -127
.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
app.py
CHANGED
|
File without changes
|
assets/model_color.json
CHANGED
|
@@ -4,6 +4,7 @@
|
|
| 4 |
"claude-3-5-sonnet-20241022": "#1A4C7C",
|
| 5 |
"claude-opus-4-20250514": "#3A80D2",
|
| 6 |
"claude-sonnet-4-20250514": "#5A9FE2",
|
|
|
|
| 7 |
"gemini-2.0-flash": "#FF4081",
|
| 8 |
"gemini-2.0-flash-thinking-exp-1219": "#C2185B",
|
| 9 |
"gemini-2.5-pro-exp-03-25": "#FF80AB",
|
|
@@ -11,47 +12,73 @@
|
|
| 11 |
"gemini-2.5-flash-preview-05-20": "#F8BBD9",
|
| 12 |
"gemini-2.5-pro-preview-05-06": "#AD1457",
|
| 13 |
"gemini-2.5-pro-preview-06-05": "#EC407A",
|
|
|
|
| 14 |
"gpt-4o-2024-11-20": "#00BFA5",
|
| 15 |
"gpt-4.5-preview-2025-02-27": "#00796B",
|
| 16 |
"gpt-4.1-2025-04-14": "#00897B",
|
|
|
|
|
|
|
|
|
|
| 17 |
"o1-2024-12-17": "#4DB6AC",
|
| 18 |
"o1-mini-2024-09-12": "#26A69A",
|
| 19 |
"o3-mini-2025-01-31(medium)": "#80CBC4",
|
| 20 |
"o3-2025-04-16": "#26C6DA",
|
| 21 |
"o4-mini-2025-04-16": "#00ACC1",
|
|
|
|
| 22 |
"grok-3-beta": "#FF7043",
|
| 23 |
"grok-3-mini-beta": "#FF8A65",
|
|
|
|
|
|
|
| 24 |
"deepseek-v3": "#FFC107",
|
| 25 |
"deepseek-r1-0120": "#FFA000",
|
| 26 |
"deepseek-r1-0528": "#FFB300",
|
|
|
|
| 27 |
"llama-4-maverick-17b-128e-instruct-fp8": "#8E24AA",
|
| 28 |
"qwen3-235B-A22B-fp8": "#6A1B9A",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
"random (x30)": "#9E9E9E",
|
| 30 |
-
|
| 31 |
-
"๐ฎ claude-3-
|
| 32 |
-
"๐ฎ claude-3-5-
|
| 33 |
-
"๐ฎ claude-
|
| 34 |
-
"๐ฎ claude-
|
| 35 |
-
"๐ฎ
|
| 36 |
-
|
| 37 |
-
"๐ฎ gemini-2.
|
| 38 |
-
"๐ฎ gemini-2.
|
| 39 |
-
"๐ฎ gemini-2.5-
|
| 40 |
-
"๐ฎ gemini-2.5-
|
| 41 |
-
"๐ฎ gemini-2.5-
|
| 42 |
-
"๐ฎ
|
| 43 |
-
"๐ฎ
|
| 44 |
-
|
| 45 |
-
"๐ฎ
|
| 46 |
-
"๐ฎ
|
| 47 |
-
"๐ฎ
|
| 48 |
-
"๐ฎ
|
| 49 |
-
"๐ฎ
|
| 50 |
-
|
| 51 |
-
"๐ฎ
|
| 52 |
-
"๐ฎ
|
| 53 |
-
"๐ฎ
|
| 54 |
-
"๐ฎ
|
| 55 |
-
"๐ฎ
|
| 56 |
-
|
| 57 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"claude-3-5-sonnet-20241022": "#1A4C7C",
|
| 5 |
"claude-opus-4-20250514": "#3A80D2",
|
| 6 |
"claude-sonnet-4-20250514": "#5A9FE2",
|
| 7 |
+
|
| 8 |
"gemini-2.0-flash": "#FF4081",
|
| 9 |
"gemini-2.0-flash-thinking-exp-1219": "#C2185B",
|
| 10 |
"gemini-2.5-pro-exp-03-25": "#FF80AB",
|
|
|
|
| 12 |
"gemini-2.5-flash-preview-05-20": "#F8BBD9",
|
| 13 |
"gemini-2.5-pro-preview-05-06": "#AD1457",
|
| 14 |
"gemini-2.5-pro-preview-06-05": "#EC407A",
|
| 15 |
+
|
| 16 |
"gpt-4o-2024-11-20": "#00BFA5",
|
| 17 |
"gpt-4.5-preview-2025-02-27": "#00796B",
|
| 18 |
"gpt-4.1-2025-04-14": "#00897B",
|
| 19 |
+
"gpt-oss-20b": "#4DD0E1",
|
| 20 |
+
"gpt-oss-120b": "#00838F",
|
| 21 |
+
|
| 22 |
"o1-2024-12-17": "#4DB6AC",
|
| 23 |
"o1-mini-2024-09-12": "#26A69A",
|
| 24 |
"o3-mini-2025-01-31(medium)": "#80CBC4",
|
| 25 |
"o3-2025-04-16": "#26C6DA",
|
| 26 |
"o4-mini-2025-04-16": "#00ACC1",
|
| 27 |
+
|
| 28 |
"grok-3-beta": "#FF7043",
|
| 29 |
"grok-3-mini-beta": "#FF8A65",
|
| 30 |
+
"grok-4-0709": "#FF7043",
|
| 31 |
+
|
| 32 |
"deepseek-v3": "#FFC107",
|
| 33 |
"deepseek-r1-0120": "#FFA000",
|
| 34 |
"deepseek-r1-0528": "#FFB300",
|
| 35 |
+
|
| 36 |
"llama-4-maverick-17b-128e-instruct-fp8": "#8E24AA",
|
| 37 |
"qwen3-235B-A22B-fp8": "#6A1B9A",
|
| 38 |
+
"kimi-k2-0711-preview": "#FA1B9A",
|
| 39 |
+
|
| 40 |
+
"glm-4.5": "#4CAF50",
|
| 41 |
+
|
| 42 |
"random (x30)": "#9E9E9E",
|
| 43 |
+
|
| 44 |
+
"๐ฎ claude-3-7-sonnet-20250219": "#4A90E2",
|
| 45 |
+
"๐ฎ claude-3-5-haiku-20241022": "#7FB5E6",
|
| 46 |
+
"๐ฎ claude-3-5-sonnet-20241022": "#1A4C7C",
|
| 47 |
+
"๐ฎ claude-opus-4-20250514": "#3A80D2",
|
| 48 |
+
"๐ฎ claude-sonnet-4-20250514": "#5A9FE2",
|
| 49 |
+
|
| 50 |
+
"๐ฎ gemini-2.0-flash": "#FF4081",
|
| 51 |
+
"๐ฎ gemini-2.0-flash-thinking-exp-1219": "#C2185B",
|
| 52 |
+
"๐ฎ gemini-2.5-pro-exp-03-25": "#FF80AB",
|
| 53 |
+
"๐ฎ gemini-2.5-flash-preview-04-17": "#F06292",
|
| 54 |
+
"๐ฎ gemini-2.5-flash-preview-05-20": "#F8BBD9",
|
| 55 |
+
"๐ฎ gemini-2.5-pro-preview-05-06": "#AD1457",
|
| 56 |
+
"๐ฎ gemini-2.5-pro-preview-06-05": "#EC407A",
|
| 57 |
+
|
| 58 |
+
"๐ฎ gpt-4o-2024-11-20": "#00BFA5",
|
| 59 |
+
"๐ฎ gpt-4.5-preview-2025-02-27": "#00796B",
|
| 60 |
+
"๐ฎ gpt-4.1-2025-04-14": "#00897B",
|
| 61 |
+
"๐ฎ gpt-oss-20b": "#4DD0E1",
|
| 62 |
+
"๐ฎ gpt-oss-120b": "#00838F",
|
| 63 |
+
|
| 64 |
+
"๐ฎ o1-2024-12-17": "#4DB6AC",
|
| 65 |
+
"๐ฎ o1-mini-2024-09-12": "#26A69A",
|
| 66 |
+
"๐ฎ o3-mini-2025-01-31(medium)": "#80CBC4",
|
| 67 |
+
"๐ฎ o3-2025-04-16": "#26C6DA",
|
| 68 |
+
"๐ฎ o4-mini-2025-04-16": "#00ACC1",
|
| 69 |
+
|
| 70 |
+
"๐ฎ grok-3-beta": "#FF7043",
|
| 71 |
+
"๐ฎ grok-3-mini-beta": "#FF8A65",
|
| 72 |
+
"๐ฎ grok-4-0709": "#FF7043",
|
| 73 |
+
|
| 74 |
+
"๐ฎ deepseek-v3": "#FFC107",
|
| 75 |
+
"๐ฎ deepseek-r1-0120": "#FFA000",
|
| 76 |
+
"๐ฎ deepseek-r1-0528": "#FFB300",
|
| 77 |
+
|
| 78 |
+
"๐ฎ llama-4-maverick-17b-128e-instruct-fp8": "#8E24AA",
|
| 79 |
+
"๐ฎ qwen3-235B-A22B-fp8": "#6A1B9A",
|
| 80 |
+
"๐ฎ kimi-k2-0711-preview": "#FA1B9A",
|
| 81 |
+
|
| 82 |
+
"๐ฎ glm-4.5": "#4CAF50"
|
| 83 |
+
}
|
| 84 |
+
|
gallery_tab.py
CHANGED
|
@@ -1,285 +1,285 @@
|
|
| 1 |
-
import gradio as gr
|
| 2 |
-
from datetime import datetime
|
| 3 |
-
import json
|
| 4 |
-
|
| 5 |
-
# Load video links and news data
|
| 6 |
-
with open('assets/game_video_link.json', 'r') as f:
|
| 7 |
-
VIDEO_LINKS = json.load(f)
|
| 8 |
-
|
| 9 |
-
with open('assets/news.json', 'r') as f:
|
| 10 |
-
NEWS_DATA = json.load(f)
|
| 11 |
-
|
| 12 |
-
def create_video_gallery():
|
| 13 |
-
"""Create a custom HTML/JS component for video gallery"""
|
| 14 |
-
# Extract video IDs
|
| 15 |
-
mario_id = VIDEO_LINKS["super_mario_bros"].split("?v=")[1]
|
| 16 |
-
sokoban_id = VIDEO_LINKS["sokoban"].split("?v=")[1]
|
| 17 |
-
game_2048_id = VIDEO_LINKS["2048"].split("?v=")[1]
|
| 18 |
-
candy_id = VIDEO_LINKS["candy"].split("?v=")[1]
|
| 19 |
-
ace_attorney_id = VIDEO_LINKS["ace_attorney"].split("?v=")[1]
|
| 20 |
-
tetris_id = VIDEO_LINKS["tetris"].split("?v=")[1]
|
| 21 |
-
|
| 22 |
-
# Get the latest video from news data
|
| 23 |
-
latest_news = NEWS_DATA["news"][0] # First item is the latest
|
| 24 |
-
latest_video_id = latest_news["video_link"].split("?v=")[1]
|
| 25 |
-
latest_date = datetime.strptime(latest_news["date"], "%Y-%m-%d")
|
| 26 |
-
formatted_latest_date = latest_date.strftime("%B %d, %Y")
|
| 27 |
-
|
| 28 |
-
# Generate news HTML
|
| 29 |
-
news_items = []
|
| 30 |
-
for item in NEWS_DATA["news"]:
|
| 31 |
-
video_id = item["video_link"].split("?v=")[1]
|
| 32 |
-
date_obj = datetime.strptime(item["date"], "%Y-%m-%d")
|
| 33 |
-
formatted_date = date_obj.strftime("%B %d, %Y")
|
| 34 |
-
news_items.append(f'''
|
| 35 |
-
<div class="news-item">
|
| 36 |
-
<div class="news-date">{formatted_date}</div>
|
| 37 |
-
<div class="news-content">
|
| 38 |
-
<div class="news-video">
|
| 39 |
-
<div class="video-wrapper">
|
| 40 |
-
<iframe src="https://www.youtube.com/embed/{video_id}"></iframe>
|
| 41 |
-
</div>
|
| 42 |
-
</div>
|
| 43 |
-
<div class="news-text">
|
| 44 |
-
<a href="{item["twitter_link"]}" target="_blank" class="twitter-link">
|
| 45 |
-
<span class="twitter-icon">๐ข</span>
|
| 46 |
-
{item["twitter_text"]}
|
| 47 |
-
</a>
|
| 48 |
-
</div>
|
| 49 |
-
</div>
|
| 50 |
-
</div>
|
| 51 |
-
''')
|
| 52 |
-
|
| 53 |
-
news_html = '\n'.join(news_items)
|
| 54 |
-
|
| 55 |
-
gallery_html = f'''
|
| 56 |
-
<div class="video-gallery-container">
|
| 57 |
-
<style>
|
| 58 |
-
.video-gallery-container {{
|
| 59 |
-
width: 100%;
|
| 60 |
-
max-width: 1400px;
|
| 61 |
-
margin: 0 auto;
|
| 62 |
-
padding: 20px;
|
| 63 |
-
}}
|
| 64 |
-
.highlight-section {{
|
| 65 |
-
margin-bottom: 40px;
|
| 66 |
-
}}
|
| 67 |
-
.highlight-card {{
|
| 68 |
-
background: #ffffff;
|
| 69 |
-
border-radius: 10px;
|
| 70 |
-
box-shadow: 0 4px 20px rgba(0,0,0,0.15);
|
| 71 |
-
overflow: hidden;
|
| 72 |
-
transition: transform 0.3s;
|
| 73 |
-
border: 2px solid #2196F3;
|
| 74 |
-
}}
|
| 75 |
-
.highlight-card:hover {{
|
| 76 |
-
transform: translateY(-5px);
|
| 77 |
-
}}
|
| 78 |
-
.highlight-header {{
|
| 79 |
-
background: #2196F3;
|
| 80 |
-
color: white;
|
| 81 |
-
padding: 15px 20px;
|
| 82 |
-
font-size: 1.2em;
|
| 83 |
-
font-weight: bold;
|
| 84 |
-
display: flex;
|
| 85 |
-
align-items: center;
|
| 86 |
-
gap: 10px;
|
| 87 |
-
}}
|
| 88 |
-
.highlight-date {{
|
| 89 |
-
font-size: 0.9em;
|
| 90 |
-
opacity: 0.9;
|
| 91 |
-
}}
|
| 92 |
-
.highlight-content {{
|
| 93 |
-
padding: 20px;
|
| 94 |
-
}}
|
| 95 |
-
.video-grid {{
|
| 96 |
-
display: grid;
|
| 97 |
-
grid-template-columns: repeat(2, 1fr);
|
| 98 |
-
gap: 20px;
|
| 99 |
-
margin-top: 20px;
|
| 100 |
-
margin-bottom: 40px;
|
| 101 |
-
}}
|
| 102 |
-
.video-card {{
|
| 103 |
-
background: var(--card-bg, #ffffff);
|
| 104 |
-
border-radius: 10px;
|
| 105 |
-
box-shadow: 0 2px 10px rgba(0,0,0,0.1);
|
| 106 |
-
overflow: hidden;
|
| 107 |
-
transition: transform 0.2s;
|
| 108 |
-
}}
|
| 109 |
-
.video-card:hover {{
|
| 110 |
-
transform: translateY(-5px);
|
| 111 |
-
}}
|
| 112 |
-
.video-wrapper {{
|
| 113 |
-
position: relative;
|
| 114 |
-
padding-bottom: 56.25%;
|
| 115 |
-
height: 0;
|
| 116 |
-
overflow: hidden;
|
| 117 |
-
}}
|
| 118 |
-
.video-wrapper iframe {{
|
| 119 |
-
position: absolute;
|
| 120 |
-
top: 0;
|
| 121 |
-
left: 0;
|
| 122 |
-
width: 100%;
|
| 123 |
-
height: 100%;
|
| 124 |
-
border: none;
|
| 125 |
-
}}
|
| 126 |
-
.video-title {{
|
| 127 |
-
padding: 15px;
|
| 128 |
-
font-size: 1.2em;
|
| 129 |
-
font-weight: bold;
|
| 130 |
-
color: var(--title-text, #2c3e50);
|
| 131 |
-
text-align: center;
|
| 132 |
-
background: var(--title-bg, #f8f9fa);
|
| 133 |
-
border-top: 1px solid var(--border-color, #eee);
|
| 134 |
-
}}
|
| 135 |
-
.news-section {{
|
| 136 |
-
margin-top: 40px;
|
| 137 |
-
border-top: 2px solid #e9ecef;
|
| 138 |
-
padding-top: 20px;
|
| 139 |
-
}}
|
| 140 |
-
.news-section-title {{
|
| 141 |
-
font-size: 1.8em;
|
| 142 |
-
font-weight: bold;
|
| 143 |
-
color: #2c3e50;
|
| 144 |
-
margin-bottom: 20px;
|
| 145 |
-
text-align: center;
|
| 146 |
-
}}
|
| 147 |
-
.news-item {{
|
| 148 |
-
background: #ffffff;
|
| 149 |
-
border-radius: 10px;
|
| 150 |
-
box-shadow: 0 2px 10px rgba(0,0,0,0.1);
|
| 151 |
-
margin-bottom: 20px;
|
| 152 |
-
overflow: hidden;
|
| 153 |
-
}}
|
| 154 |
-
.news-date {{
|
| 155 |
-
padding: 10px 20px;
|
| 156 |
-
background: #f8f9fa;
|
| 157 |
-
color: #666;
|
| 158 |
-
font-size: 0.9em;
|
| 159 |
-
border-bottom: 1px solid #eee;
|
| 160 |
-
}}
|
| 161 |
-
.news-content {{
|
| 162 |
-
display: flex;
|
| 163 |
-
padding: 20px;
|
| 164 |
-
align-items: center;
|
| 165 |
-
gap: 30px;
|
| 166 |
-
}}
|
| 167 |
-
.news-video {{
|
| 168 |
-
flex: 0 0 300px;
|
| 169 |
-
}}
|
| 170 |
-
.news-text {{
|
| 171 |
-
flex: 1;
|
| 172 |
-
display: flex;
|
| 173 |
-
align-items: center;
|
| 174 |
-
min-height: 169px;
|
| 175 |
-
}}
|
| 176 |
-
.twitter-link {{
|
| 177 |
-
color: #2c3e50;
|
| 178 |
-
text-decoration: none;
|
| 179 |
-
display: flex;
|
| 180 |
-
align-items: center;
|
| 181 |
-
gap: 15px;
|
| 182 |
-
font-size: 1.4em;
|
| 183 |
-
font-weight: 600;
|
| 184 |
-
line-height: 1.4;
|
| 185 |
-
}}
|
| 186 |
-
.twitter-link:hover {{
|
| 187 |
-
color: #1da1f2;
|
| 188 |
-
}}
|
| 189 |
-
.twitter-icon {{
|
| 190 |
-
font-size: 1.5em;
|
| 191 |
-
color: #1da1f2;
|
| 192 |
-
}}
|
| 193 |
-
|
| 194 |
-
/* Dark mode specific styles */
|
| 195 |
-
.dark .video-card {{
|
| 196 |
-
--card-bg: #2d3748;
|
| 197 |
-
--title-bg: #1a202c;
|
| 198 |
-
--title-text: #e2e8f0;
|
| 199 |
-
--border-color: #4a5568;
|
| 200 |
-
}}
|
| 201 |
-
|
| 202 |
-
/* Light mode specific styles */
|
| 203 |
-
.light .video-card {{
|
| 204 |
-
--card-bg: #ffffff;
|
| 205 |
-
--title-bg: #f8f9fa;
|
| 206 |
-
--title-text: #2c3e50;
|
| 207 |
-
--border-color: #eee;
|
| 208 |
-
}}
|
| 209 |
-
</style>
|
| 210 |
-
|
| 211 |
-
<!-- Highlight Section -->
|
| 212 |
-
<div class="highlight-section">
|
| 213 |
-
<div class="highlight-card">
|
| 214 |
-
<div class="highlight-header">
|
| 215 |
-
<span>๐ Latest Update</span>
|
| 216 |
-
<span class="highlight-date">{formatted_latest_date}</span>
|
| 217 |
-
</div>
|
| 218 |
-
<div class="highlight-content">
|
| 219 |
-
<div class="video-wrapper">
|
| 220 |
-
<iframe src="https://www.youtube.com/embed/{latest_video_id}"></iframe>
|
| 221 |
-
</div>
|
| 222 |
-
<div class="video-title">
|
| 223 |
-
<a href="{latest_news["twitter_link"]}" target="_blank" class="twitter-link">
|
| 224 |
-
<span class="twitter-icon">๐ข</span>
|
| 225 |
-
{latest_news["twitter_text"]}
|
| 226 |
-
</a>
|
| 227 |
-
</div>
|
| 228 |
-
</div>
|
| 229 |
-
</div>
|
| 230 |
-
</div>
|
| 231 |
-
|
| 232 |
-
<!-- Regular Video Grid -->
|
| 233 |
-
<div class="video-grid">
|
| 234 |
-
<div class="video-card">
|
| 235 |
-
<div class="video-wrapper">
|
| 236 |
-
<iframe src="https://www.youtube.com/embed/{mario_id}"></iframe>
|
| 237 |
-
</div>
|
| 238 |
-
<div class="video-title">๐ฎ Super Mario Bros</div>
|
| 239 |
-
</div>
|
| 240 |
-
<div class="video-card">
|
| 241 |
-
<div class="video-wrapper">
|
| 242 |
-
<iframe src="https://www.youtube.com/embed/{sokoban_id}"></iframe>
|
| 243 |
-
</div>
|
| 244 |
-
<div class="video-title">๐ฆ Sokoban</div>
|
| 245 |
-
</div>
|
| 246 |
-
<div class="video-card">
|
| 247 |
-
<div class="video-wrapper">
|
| 248 |
-
<iframe src="https://www.youtube.com/embed/{game_2048_id}"></iframe>
|
| 249 |
-
</div>
|
| 250 |
-
<div class="video-title">๐ข 2048</div>
|
| 251 |
-
</div>
|
| 252 |
-
<div class="video-card">
|
| 253 |
-
<div class="video-wrapper">
|
| 254 |
-
<iframe src="https://www.youtube.com/embed/{candy_id}"></iframe>
|
| 255 |
-
</div>
|
| 256 |
-
<div class="video-title">๐ฌ Candy Crush</div>
|
| 257 |
-
</div>
|
| 258 |
-
<div class="video-card">
|
| 259 |
-
<div class="video-wrapper">
|
| 260 |
-
<iframe src="https://www.youtube.com/embed/{ace_attorney_id}"></iframe>
|
| 261 |
-
</div>
|
| 262 |
-
<div class="video-title">โ๏ธ Ace Attorney</div>
|
| 263 |
-
</div>
|
| 264 |
-
<div class="video-card">
|
| 265 |
-
<div class="video-wrapper">
|
| 266 |
-
<iframe src="https://www.youtube.com/embed/{tetris_id}"></iframe>
|
| 267 |
-
</div>
|
| 268 |
-
<div class="video-title">๐งฉ Tetris</div>
|
| 269 |
-
</div>
|
| 270 |
-
</div>
|
| 271 |
-
|
| 272 |
-
<!-- News Section -->
|
| 273 |
-
<div class="news-section">
|
| 274 |
-
<div class="news-section-title">๐ฐ Latest News</div>
|
| 275 |
-
{news_html}
|
| 276 |
-
</div>
|
| 277 |
-
</div>
|
| 278 |
-
'''
|
| 279 |
-
return gr.HTML(gallery_html)
|
| 280 |
-
|
| 281 |
-
def create_gallery_tab():
|
| 282 |
-
"""Create and return the gallery tab component"""
|
| 283 |
-
with gr.Tab("๐ฅ Gallery") as gallery_tab:
|
| 284 |
-
video_gallery = create_video_gallery()
|
| 285 |
return gallery_tab
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
from datetime import datetime
|
| 3 |
+
import json
|
| 4 |
+
|
| 5 |
+
# Load video links and news data
|
| 6 |
+
with open('assets/game_video_link.json', 'r') as f:
|
| 7 |
+
VIDEO_LINKS = json.load(f)
|
| 8 |
+
|
| 9 |
+
with open('assets/news.json', 'r') as f:
|
| 10 |
+
NEWS_DATA = json.load(f)
|
| 11 |
+
|
| 12 |
+
def create_video_gallery():
|
| 13 |
+
"""Create a custom HTML/JS component for video gallery"""
|
| 14 |
+
# Extract video IDs
|
| 15 |
+
mario_id = VIDEO_LINKS["super_mario_bros"].split("?v=")[1]
|
| 16 |
+
sokoban_id = VIDEO_LINKS["sokoban"].split("?v=")[1]
|
| 17 |
+
game_2048_id = VIDEO_LINKS["2048"].split("?v=")[1]
|
| 18 |
+
candy_id = VIDEO_LINKS["candy"].split("?v=")[1]
|
| 19 |
+
ace_attorney_id = VIDEO_LINKS["ace_attorney"].split("?v=")[1]
|
| 20 |
+
tetris_id = VIDEO_LINKS["tetris"].split("?v=")[1]
|
| 21 |
+
|
| 22 |
+
# Get the latest video from news data
|
| 23 |
+
latest_news = NEWS_DATA["news"][0] # First item is the latest
|
| 24 |
+
latest_video_id = latest_news["video_link"].split("?v=")[1]
|
| 25 |
+
latest_date = datetime.strptime(latest_news["date"], "%Y-%m-%d")
|
| 26 |
+
formatted_latest_date = latest_date.strftime("%B %d, %Y")
|
| 27 |
+
|
| 28 |
+
# Generate news HTML
|
| 29 |
+
news_items = []
|
| 30 |
+
for item in NEWS_DATA["news"]:
|
| 31 |
+
video_id = item["video_link"].split("?v=")[1]
|
| 32 |
+
date_obj = datetime.strptime(item["date"], "%Y-%m-%d")
|
| 33 |
+
formatted_date = date_obj.strftime("%B %d, %Y")
|
| 34 |
+
news_items.append(f'''
|
| 35 |
+
<div class="news-item">
|
| 36 |
+
<div class="news-date">{formatted_date}</div>
|
| 37 |
+
<div class="news-content">
|
| 38 |
+
<div class="news-video">
|
| 39 |
+
<div class="video-wrapper">
|
| 40 |
+
<iframe src="https://www.youtube.com/embed/{video_id}"></iframe>
|
| 41 |
+
</div>
|
| 42 |
+
</div>
|
| 43 |
+
<div class="news-text">
|
| 44 |
+
<a href="{item["twitter_link"]}" target="_blank" class="twitter-link">
|
| 45 |
+
<span class="twitter-icon">๐ข</span>
|
| 46 |
+
{item["twitter_text"]}
|
| 47 |
+
</a>
|
| 48 |
+
</div>
|
| 49 |
+
</div>
|
| 50 |
+
</div>
|
| 51 |
+
''')
|
| 52 |
+
|
| 53 |
+
news_html = '\n'.join(news_items)
|
| 54 |
+
|
| 55 |
+
gallery_html = f'''
|
| 56 |
+
<div class="video-gallery-container">
|
| 57 |
+
<style>
|
| 58 |
+
.video-gallery-container {{
|
| 59 |
+
width: 100%;
|
| 60 |
+
max-width: 1400px;
|
| 61 |
+
margin: 0 auto;
|
| 62 |
+
padding: 20px;
|
| 63 |
+
}}
|
| 64 |
+
.highlight-section {{
|
| 65 |
+
margin-bottom: 40px;
|
| 66 |
+
}}
|
| 67 |
+
.highlight-card {{
|
| 68 |
+
background: #ffffff;
|
| 69 |
+
border-radius: 10px;
|
| 70 |
+
box-shadow: 0 4px 20px rgba(0,0,0,0.15);
|
| 71 |
+
overflow: hidden;
|
| 72 |
+
transition: transform 0.3s;
|
| 73 |
+
border: 2px solid #2196F3;
|
| 74 |
+
}}
|
| 75 |
+
.highlight-card:hover {{
|
| 76 |
+
transform: translateY(-5px);
|
| 77 |
+
}}
|
| 78 |
+
.highlight-header {{
|
| 79 |
+
background: #2196F3;
|
| 80 |
+
color: white;
|
| 81 |
+
padding: 15px 20px;
|
| 82 |
+
font-size: 1.2em;
|
| 83 |
+
font-weight: bold;
|
| 84 |
+
display: flex;
|
| 85 |
+
align-items: center;
|
| 86 |
+
gap: 10px;
|
| 87 |
+
}}
|
| 88 |
+
.highlight-date {{
|
| 89 |
+
font-size: 0.9em;
|
| 90 |
+
opacity: 0.9;
|
| 91 |
+
}}
|
| 92 |
+
.highlight-content {{
|
| 93 |
+
padding: 20px;
|
| 94 |
+
}}
|
| 95 |
+
.video-grid {{
|
| 96 |
+
display: grid;
|
| 97 |
+
grid-template-columns: repeat(2, 1fr);
|
| 98 |
+
gap: 20px;
|
| 99 |
+
margin-top: 20px;
|
| 100 |
+
margin-bottom: 40px;
|
| 101 |
+
}}
|
| 102 |
+
.video-card {{
|
| 103 |
+
background: var(--card-bg, #ffffff);
|
| 104 |
+
border-radius: 10px;
|
| 105 |
+
box-shadow: 0 2px 10px rgba(0,0,0,0.1);
|
| 106 |
+
overflow: hidden;
|
| 107 |
+
transition: transform 0.2s;
|
| 108 |
+
}}
|
| 109 |
+
.video-card:hover {{
|
| 110 |
+
transform: translateY(-5px);
|
| 111 |
+
}}
|
| 112 |
+
.video-wrapper {{
|
| 113 |
+
position: relative;
|
| 114 |
+
padding-bottom: 56.25%;
|
| 115 |
+
height: 0;
|
| 116 |
+
overflow: hidden;
|
| 117 |
+
}}
|
| 118 |
+
.video-wrapper iframe {{
|
| 119 |
+
position: absolute;
|
| 120 |
+
top: 0;
|
| 121 |
+
left: 0;
|
| 122 |
+
width: 100%;
|
| 123 |
+
height: 100%;
|
| 124 |
+
border: none;
|
| 125 |
+
}}
|
| 126 |
+
.video-title {{
|
| 127 |
+
padding: 15px;
|
| 128 |
+
font-size: 1.2em;
|
| 129 |
+
font-weight: bold;
|
| 130 |
+
color: var(--title-text, #2c3e50);
|
| 131 |
+
text-align: center;
|
| 132 |
+
background: var(--title-bg, #f8f9fa);
|
| 133 |
+
border-top: 1px solid var(--border-color, #eee);
|
| 134 |
+
}}
|
| 135 |
+
.news-section {{
|
| 136 |
+
margin-top: 40px;
|
| 137 |
+
border-top: 2px solid #e9ecef;
|
| 138 |
+
padding-top: 20px;
|
| 139 |
+
}}
|
| 140 |
+
.news-section-title {{
|
| 141 |
+
font-size: 1.8em;
|
| 142 |
+
font-weight: bold;
|
| 143 |
+
color: #2c3e50;
|
| 144 |
+
margin-bottom: 20px;
|
| 145 |
+
text-align: center;
|
| 146 |
+
}}
|
| 147 |
+
.news-item {{
|
| 148 |
+
background: #ffffff;
|
| 149 |
+
border-radius: 10px;
|
| 150 |
+
box-shadow: 0 2px 10px rgba(0,0,0,0.1);
|
| 151 |
+
margin-bottom: 20px;
|
| 152 |
+
overflow: hidden;
|
| 153 |
+
}}
|
| 154 |
+
.news-date {{
|
| 155 |
+
padding: 10px 20px;
|
| 156 |
+
background: #f8f9fa;
|
| 157 |
+
color: #666;
|
| 158 |
+
font-size: 0.9em;
|
| 159 |
+
border-bottom: 1px solid #eee;
|
| 160 |
+
}}
|
| 161 |
+
.news-content {{
|
| 162 |
+
display: flex;
|
| 163 |
+
padding: 20px;
|
| 164 |
+
align-items: center;
|
| 165 |
+
gap: 30px;
|
| 166 |
+
}}
|
| 167 |
+
.news-video {{
|
| 168 |
+
flex: 0 0 300px;
|
| 169 |
+
}}
|
| 170 |
+
.news-text {{
|
| 171 |
+
flex: 1;
|
| 172 |
+
display: flex;
|
| 173 |
+
align-items: center;
|
| 174 |
+
min-height: 169px;
|
| 175 |
+
}}
|
| 176 |
+
.twitter-link {{
|
| 177 |
+
color: #2c3e50;
|
| 178 |
+
text-decoration: none;
|
| 179 |
+
display: flex;
|
| 180 |
+
align-items: center;
|
| 181 |
+
gap: 15px;
|
| 182 |
+
font-size: 1.4em;
|
| 183 |
+
font-weight: 600;
|
| 184 |
+
line-height: 1.4;
|
| 185 |
+
}}
|
| 186 |
+
.twitter-link:hover {{
|
| 187 |
+
color: #1da1f2;
|
| 188 |
+
}}
|
| 189 |
+
.twitter-icon {{
|
| 190 |
+
font-size: 1.5em;
|
| 191 |
+
color: #1da1f2;
|
| 192 |
+
}}
|
| 193 |
+
|
| 194 |
+
/* Dark mode specific styles */
|
| 195 |
+
.dark .video-card {{
|
| 196 |
+
--card-bg: #2d3748;
|
| 197 |
+
--title-bg: #1a202c;
|
| 198 |
+
--title-text: #e2e8f0;
|
| 199 |
+
--border-color: #4a5568;
|
| 200 |
+
}}
|
| 201 |
+
|
| 202 |
+
/* Light mode specific styles */
|
| 203 |
+
.light .video-card {{
|
| 204 |
+
--card-bg: #ffffff;
|
| 205 |
+
--title-bg: #f8f9fa;
|
| 206 |
+
--title-text: #2c3e50;
|
| 207 |
+
--border-color: #eee;
|
| 208 |
+
}}
|
| 209 |
+
</style>
|
| 210 |
+
|
| 211 |
+
<!-- Highlight Section -->
|
| 212 |
+
<div class="highlight-section">
|
| 213 |
+
<div class="highlight-card">
|
| 214 |
+
<div class="highlight-header">
|
| 215 |
+
<span>๐ Latest Update</span>
|
| 216 |
+
<span class="highlight-date">{formatted_latest_date}</span>
|
| 217 |
+
</div>
|
| 218 |
+
<div class="highlight-content">
|
| 219 |
+
<div class="video-wrapper">
|
| 220 |
+
<iframe src="https://www.youtube.com/embed/{latest_video_id}"></iframe>
|
| 221 |
+
</div>
|
| 222 |
+
<div class="video-title">
|
| 223 |
+
<a href="{latest_news["twitter_link"]}" target="_blank" class="twitter-link">
|
| 224 |
+
<span class="twitter-icon">๐ข</span>
|
| 225 |
+
{latest_news["twitter_text"]}
|
| 226 |
+
</a>
|
| 227 |
+
</div>
|
| 228 |
+
</div>
|
| 229 |
+
</div>
|
| 230 |
+
</div>
|
| 231 |
+
|
| 232 |
+
<!-- Regular Video Grid -->
|
| 233 |
+
<div class="video-grid">
|
| 234 |
+
<div class="video-card">
|
| 235 |
+
<div class="video-wrapper">
|
| 236 |
+
<iframe src="https://www.youtube.com/embed/{mario_id}"></iframe>
|
| 237 |
+
</div>
|
| 238 |
+
<div class="video-title">๐ฎ Super Mario Bros</div>
|
| 239 |
+
</div>
|
| 240 |
+
<div class="video-card">
|
| 241 |
+
<div class="video-wrapper">
|
| 242 |
+
<iframe src="https://www.youtube.com/embed/{sokoban_id}"></iframe>
|
| 243 |
+
</div>
|
| 244 |
+
<div class="video-title">๐ฆ Sokoban</div>
|
| 245 |
+
</div>
|
| 246 |
+
<div class="video-card">
|
| 247 |
+
<div class="video-wrapper">
|
| 248 |
+
<iframe src="https://www.youtube.com/embed/{game_2048_id}"></iframe>
|
| 249 |
+
</div>
|
| 250 |
+
<div class="video-title">๐ข 2048</div>
|
| 251 |
+
</div>
|
| 252 |
+
<div class="video-card">
|
| 253 |
+
<div class="video-wrapper">
|
| 254 |
+
<iframe src="https://www.youtube.com/embed/{candy_id}"></iframe>
|
| 255 |
+
</div>
|
| 256 |
+
<div class="video-title">๐ฌ Candy Crush</div>
|
| 257 |
+
</div>
|
| 258 |
+
<div class="video-card">
|
| 259 |
+
<div class="video-wrapper">
|
| 260 |
+
<iframe src="https://www.youtube.com/embed/{ace_attorney_id}"></iframe>
|
| 261 |
+
</div>
|
| 262 |
+
<div class="video-title">โ๏ธ Ace Attorney</div>
|
| 263 |
+
</div>
|
| 264 |
+
<div class="video-card">
|
| 265 |
+
<div class="video-wrapper">
|
| 266 |
+
<iframe src="https://www.youtube.com/embed/{tetris_id}"></iframe>
|
| 267 |
+
</div>
|
| 268 |
+
<div class="video-title">๐งฉ Tetris</div>
|
| 269 |
+
</div>
|
| 270 |
+
</div>
|
| 271 |
+
|
| 272 |
+
<!-- News Section -->
|
| 273 |
+
<div class="news-section">
|
| 274 |
+
<div class="news-section-title">๐ฐ Latest News</div>
|
| 275 |
+
{news_html}
|
| 276 |
+
</div>
|
| 277 |
+
</div>
|
| 278 |
+
'''
|
| 279 |
+
return gr.HTML(gallery_html)
|
| 280 |
+
|
| 281 |
+
def create_gallery_tab():
|
| 282 |
+
"""Create and return the gallery tab component"""
|
| 283 |
+
with gr.Tab("๐ฅ Gallery") as gallery_tab:
|
| 284 |
+
video_gallery = create_video_gallery()
|
| 285 |
return gallery_tab
|
leaderboard_utils.py
CHANGED
|
@@ -28,6 +28,12 @@ def get_organization(model_name):
|
|
| 28 |
return "meta"
|
| 29 |
elif "grok" in m:
|
| 30 |
return "xai"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
else:
|
| 32 |
return "unknown"
|
| 33 |
|
|
|
|
| 28 |
return "meta"
|
| 29 |
elif "grok" in m:
|
| 30 |
return "xai"
|
| 31 |
+
elif "qwen" in m:
|
| 32 |
+
return "alibaba"
|
| 33 |
+
elif "glm" in m:
|
| 34 |
+
return "zhipu"
|
| 35 |
+
elif "kimi" in m:
|
| 36 |
+
return "moonshot"
|
| 37 |
else:
|
| 38 |
return "unknown"
|
| 39 |
|
rank_data_03_25_2025.json
CHANGED
|
@@ -3,69 +3,69 @@
|
|
| 3 |
"runs": 3,
|
| 4 |
"results": [
|
| 5 |
{
|
| 6 |
-
"model": "๐ฎ claude-3-5-sonnet-20241022
|
| 7 |
"score": 1267.7,
|
| 8 |
-
"detail_data":
|
| 9 |
"progress": "1-1"
|
| 10 |
},
|
| 11 |
{
|
| 12 |
-
"model": "๐ฎ claude-3-7-sonnet-20250219
|
| 13 |
"score": 1418.7,
|
| 14 |
-
"detail_data":
|
| 15 |
"progress": "1-1"
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"model": "๐ฎ gemini-2.5-flash-preview-04-17
|
| 19 |
"score": 1385.0,
|
| 20 |
-
"detail_data":
|
| 21 |
"progress": "1-1"
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"model": "๐ฎ gemini-2.5-pro-preview-05-06
|
| 25 |
"score": 1498.3,
|
| 26 |
-
"detail_data":
|
| 27 |
"progress": "1-1"
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"model": "๐ฎ llama-4-maverick-17b-128e-instruct-fp8
|
| 31 |
"score": 1468.7,
|
| 32 |
-
"detail_data":
|
| 33 |
"progress": "1-1"
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"model": "๐ฎ gpt-4.1-2025-04-14
|
| 37 |
"score": 2126.3,
|
| 38 |
-
"detail_data":
|
| 39 |
"progress": "1-1"
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"model": "๐ฎ gpt-4o-2024-11-20
|
| 43 |
"score": 2047.3,
|
| 44 |
-
"detail_data":
|
| 45 |
"progress": "1-1"
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"model": "๐ฎ o1-2024-12-17
|
| 49 |
"score": 855,
|
| 50 |
-
"detail_data":
|
| 51 |
"progress": "1-1"
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"model": "๐ฎ o3-2025-04-16
|
| 55 |
"score": 3445,
|
| 56 |
-
"detail_data":
|
| 57 |
"progress": "1-1"
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"model": "๐ฎ o4-mini-2025-04-16
|
| 61 |
"score": 1448.0,
|
| 62 |
-
"detail_data":
|
| 63 |
"progress": "1-1"
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"model": "random (x30)",
|
| 67 |
"score": 986.97,
|
| 68 |
-
"detail_data":
|
| 69 |
"progress": "1-1"
|
| 70 |
}
|
| 71 |
]
|
|
@@ -74,79 +74,79 @@
|
|
| 74 |
"runs": 3,
|
| 75 |
"results": [
|
| 76 |
{
|
| 77 |
-
"model": "๐ฎ claude-3-5-sonnet-20241022
|
| 78 |
"score": 1914.67,
|
| 79 |
"details": "1352,2860,1532",
|
| 80 |
"highest_tail": 256
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"model": "๐ฎ claude-3-7-sonnet-20250219
|
| 84 |
"score": 2624,
|
| 85 |
"details": "2560,3224,2088",
|
| 86 |
"highest_tail": 256
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"model": "๐ฎ deepseek-r1-0120
|
| 90 |
"score": 1873.33,
|
| 91 |
"details": "700,1240,3680",
|
| 92 |
"highest_tail": 256
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"model": "๐ฎ gemini-2.5-flash-preview-04-17
|
| 96 |
"score": 1697.33,
|
| 97 |
"details": "1304,1316,2472",
|
| 98 |
"highest_tail": 256
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"model": "๐ฎ gemini-2.5-pro-preview-05-06
|
| 102 |
"score": 3586.67,
|
| 103 |
"details": "5300,2400,3060",
|
| 104 |
"highest_tail": 512
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"model": "๐ฎ grok-3-mini-beta
|
| 108 |
"score": 4036,
|
| 109 |
"details": "6412,2492,3204",
|
| 110 |
"highest_tail": 512
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"model": "๐ฎ llama-4-maverick-17b-128e-instruct-fp8
|
| 114 |
"score": 1586.67,
|
| 115 |
"details": "1404,1272,2084",
|
| 116 |
"highest_tail": 128
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"model": "๐ฎ gpt-4.1-2025-04-14
|
| 120 |
"score": 1656,
|
| 121 |
"details": "1156,2664,1148",
|
| 122 |
"highest_tail": 256
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"model": "๐ฎ gpt-4o-2024-11-20
|
| 126 |
"score": 1656,
|
| 127 |
"details": "1604,1284,2080",
|
| 128 |
"highest_tail": 256
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"model": "๐ฎ o1-2024-12-17
|
| 132 |
"score": 7580,
|
| 133 |
"details": "7580",
|
| 134 |
"highest_tail": 512
|
| 135 |
},
|
| 136 |
{
|
| 137 |
-
"model": "๐ฎ o1-mini-2024-09-12
|
| 138 |
"score": 2757.33,
|
| 139 |
"details": "3132,2004,3136",
|
| 140 |
"highest_tail": 256
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"model": "๐ฎ o3-2025-04-16
|
| 144 |
"score": 7120,
|
| 145 |
"details": "7120",
|
| 146 |
"highest_tail": 512
|
| 147 |
},
|
| 148 |
{
|
| 149 |
-
"model": "๐ฎ o4-mini-2025-04-16
|
| 150 |
"score": 4432.0,
|
| 151 |
"details": "4928,5456,2912",
|
| 152 |
"highest_tail": 512
|
|
@@ -158,27 +158,63 @@
|
|
| 158 |
"highest_tail": 128
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"model": "๐ฎ claude-opus-4-20250514
|
| 162 |
"score": 3036.0,
|
| 163 |
"details": "3036.0",
|
| 164 |
"highest_tail": 256
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"model": "๐ฎ claude-sonnet-4-20250514
|
| 168 |
"score": 3136,
|
| 169 |
-
"details": "2148,2360,4900",
|
| 170 |
"highest_tail": 256
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"model": "๐ฎ deepseek-r1-0528
|
| 174 |
"score": 3330.0,
|
| 175 |
-
"details": "3260,3400",
|
| 176 |
"highest_tail": 256
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"model": "๐ฎ qwen3-235B-A22B-fp8
|
| 180 |
"score": 2144.0,
|
| 181 |
-
"details": "1436,2556,2440",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 182 |
"highest_tail": 256
|
| 183 |
}
|
| 184 |
]
|
|
@@ -187,67 +223,67 @@
|
|
| 187 |
"runs": 3,
|
| 188 |
"results": [
|
| 189 |
{
|
| 190 |
-
"model": "๐ฎ claude-3-5-sonnet-20241022
|
| 191 |
"score": 14.7,
|
| 192 |
"details": "16,14,14"
|
| 193 |
},
|
| 194 |
{
|
| 195 |
-
"model": "๐ฎ claude-3-7-sonnet-20250219
|
| 196 |
"score": 16.3,
|
| 197 |
"details": "19,15,15"
|
| 198 |
},
|
| 199 |
{
|
| 200 |
-
"model": "๐ฎ deepseek-r1-0120
|
| 201 |
"score": 14.3,
|
| 202 |
"details": "15,14,14"
|
| 203 |
},
|
| 204 |
{
|
| 205 |
-
"model": "๐ฎ gemini-2.5-flash-preview-04-17
|
| 206 |
"score": 16.3,
|
| 207 |
"details": "20,14,15"
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"model": "๐ฎ gemini-2.5-pro-preview-05-06
|
| 211 |
"score": 23.3,
|
| 212 |
"details": "23,23,24"
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"model": "๐ฎ grok-3-mini-beta
|
| 216 |
"score": 21.3,
|
| 217 |
"details": "20,15,29"
|
| 218 |
},
|
| 219 |
{
|
| 220 |
-
"model": "๐ฎ llama-4-maverick-17b-128e-instruct-fp8
|
| 221 |
"score": 10.3,
|
| 222 |
"details": "9,10,12"
|
| 223 |
},
|
| 224 |
{
|
| 225 |
-
"model": "๐ฎ gpt-4.1-2025-04-14
|
| 226 |
"score": 13.7,
|
| 227 |
"details": "13,14,14"
|
| 228 |
},
|
| 229 |
{
|
| 230 |
-
"model": "๐ฎ gpt-4o-2024-11-20
|
| 231 |
"score": 14,
|
| 232 |
"details": "18,11,13"
|
| 233 |
},
|
| 234 |
{
|
| 235 |
-
"model": "๐ฎ o1-2024-12-17
|
| 236 |
"score": 35,
|
| 237 |
"details": "35"
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"model": "๐ฎ o1-mini-2024-09-12
|
| 241 |
"score": 11.7,
|
| 242 |
"details": "11,11,13"
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"model": "๐ฎ o3-2025-04-16
|
| 246 |
"score": 42,
|
| 247 |
"details": "42"
|
| 248 |
},
|
| 249 |
{
|
| 250 |
-
"model": "๐ฎ o4-mini-2025-04-16
|
| 251 |
"score": 25.3,
|
| 252 |
"details": "22,35,19"
|
| 253 |
},
|
|
@@ -257,24 +293,54 @@
|
|
| 257 |
"details": ""
|
| 258 |
},
|
| 259 |
{
|
| 260 |
-
"model": "๐ฎ claude-opus-4-20250514
|
| 261 |
"score": 20,
|
| 262 |
"details": "17,18,25"
|
| 263 |
},
|
| 264 |
{
|
| 265 |
-
"model": "๐ฎ claude-sonnet-4-20250514
|
| 266 |
"score": 19.33,
|
| 267 |
"details": "20,17,21"
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"model": "๐ฎ deepseek-r1-0528
|
| 271 |
"score": 33.67,
|
| 272 |
"details": "26,34,41"
|
| 273 |
},
|
| 274 |
{
|
| 275 |
-
"model": "๐ฎ qwen3-235B-A22B-fp8
|
| 276 |
"score": 11.67,
|
| 277 |
"details": "13,14,8"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 278 |
}
|
| 279 |
]
|
| 280 |
},
|
|
@@ -282,67 +348,67 @@
|
|
| 282 |
"runs": 3,
|
| 283 |
"results": [
|
| 284 |
{
|
| 285 |
-
"model": "๐ฎ claude-3-5-sonnet-20241022
|
| 286 |
"score": 106,
|
| 287 |
"details": "92,165,61"
|
| 288 |
},
|
| 289 |
{
|
| 290 |
-
"model": "๐ฎ claude-3-7-sonnet-20250219
|
| 291 |
"score": 484,
|
| 292 |
"details": "535,428,489"
|
| 293 |
},
|
| 294 |
{
|
| 295 |
-
"model": "๐ฎ deepseek-r1-0120
|
| 296 |
"score": 447.3,
|
| 297 |
"details": "409,436,497"
|
| 298 |
},
|
| 299 |
{
|
| 300 |
-
"model": "๐ฎ gemini-2.5-flash-preview-04-17
|
| 301 |
"score": 334.7,
|
| 302 |
"details": "259,372,373"
|
| 303 |
},
|
| 304 |
{
|
| 305 |
-
"model": "๐ฎ gemini-2.5-pro-preview-05-06
|
| 306 |
"score": 416.3,
|
| 307 |
"details": "411,414,424"
|
| 308 |
},
|
| 309 |
{
|
| 310 |
-
"model": "๐ฎ grok-3-mini-beta
|
| 311 |
"score": 254,
|
| 312 |
"details": "299,332,131"
|
| 313 |
},
|
| 314 |
{
|
| 315 |
-
"model": "๐ฎ llama-4-maverick-17b-128e-instruct-fp8
|
| 316 |
"score": 128.7,
|
| 317 |
"details": "67,139,180"
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"model": "๐ฎ gpt-4.1-2025-04-14
|
| 321 |
"score": 182,
|
| 322 |
"details": "163,215,168"
|
| 323 |
},
|
| 324 |
{
|
| 325 |
-
"model": "๐ฎ gpt-4o-2024-11-20
|
| 326 |
"score": 147.3,
|
| 327 |
"details": "131,104,207"
|
| 328 |
},
|
| 329 |
{
|
| 330 |
-
"model": "๐ฎ o1-2024-12-17
|
| 331 |
"score": 159,
|
| 332 |
"details": "159"
|
| 333 |
},
|
| 334 |
{
|
| 335 |
-
"model": "๐ฎ o1-mini-2024-09-12
|
| 336 |
"score": 48,
|
| 337 |
"details": "21,86,37"
|
| 338 |
},
|
| 339 |
{
|
| 340 |
-
"model": "๐ฎ o3-2025-04-16
|
| 341 |
"score": 647,
|
| 342 |
"details": "647"
|
| 343 |
},
|
| 344 |
{
|
| 345 |
-
"model": "๐ฎ o4-mini-2025-04-16
|
| 346 |
"score": 487.3,
|
| 347 |
"details": "259,591,612"
|
| 348 |
},
|
|
@@ -352,24 +418,54 @@
|
|
| 352 |
"details": ""
|
| 353 |
},
|
| 354 |
{
|
| 355 |
-
"model": "๐ฎ claude-opus-4-20250514
|
| 356 |
"score": 464,
|
| 357 |
"details": "593,406,393"
|
| 358 |
},
|
| 359 |
{
|
| 360 |
-
"model": "๐ฎ claude-sonnet-4-20250514
|
| 361 |
"score": 478.33,
|
| 362 |
"details": "545,468,422"
|
| 363 |
},
|
| 364 |
{
|
| 365 |
-
"model": "๐ฎ deepseek-r1-0528
|
| 366 |
"score": 491.67,
|
| 367 |
"details": "464,463,548"
|
| 368 |
},
|
| 369 |
{
|
| 370 |
-
"model": "๐ฎ qwen3-235B-A22B-fp8
|
| 371 |
"score": 363.33,
|
| 372 |
"details": "365,372,353"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 373 |
}
|
| 374 |
]
|
| 375 |
},
|
|
@@ -377,108 +473,148 @@
|
|
| 377 |
"runs": 3,
|
| 378 |
"results": [
|
| 379 |
{
|
| 380 |
-
"model": "๐ฎ claude-3-5-sonnet-20241022
|
| 381 |
"score": 0,
|
| 382 |
-
"detail_box_on_target":
|
| 383 |
"cracked_levels": "0,0,0"
|
| 384 |
},
|
| 385 |
{
|
| 386 |
-
"model": "๐ฎ claude-3-7-sonnet-20250219
|
| 387 |
"score": 2.33,
|
| 388 |
-
"detail_box_on_target":
|
| 389 |
"cracked_levels": "1,2,0"
|
| 390 |
},
|
| 391 |
{
|
| 392 |
-
"model": "๐ฎ deepseek-r1-0120
|
| 393 |
"score": 1.33,
|
| 394 |
-
"detail_box_on_target":
|
| 395 |
"cracked_levels": "1,0,1"
|
| 396 |
},
|
| 397 |
{
|
| 398 |
-
"model": "๐ฎ gemini-2.5-flash-preview-04-17
|
| 399 |
"score": 1.67,
|
| 400 |
-
"detail_box_on_target":
|
| 401 |
"cracked_levels": "2,0,1"
|
| 402 |
},
|
| 403 |
{
|
| 404 |
-
"model": "๐ฎ gemini-2.5-pro-preview-05-06
|
| 405 |
"score": 4.33,
|
| 406 |
-
"detail_box_on_target":
|
| 407 |
"cracked_levels": "2,2,3"
|
| 408 |
},
|
| 409 |
{
|
| 410 |
-
"model": "๐ฎ grok-3-mini-beta
|
| 411 |
"score": 5.67,
|
| 412 |
-
"detail_box_on_target":
|
| 413 |
"cracked_levels": "3,3,3"
|
| 414 |
},
|
| 415 |
{
|
| 416 |
-
"model": "๐ฎ llama-4-maverick-17b-128e-instruct-fp8
|
| 417 |
"score": 0,
|
| 418 |
-
"detail_box_on_target":
|
| 419 |
"cracked_levels": "0,0,0"
|
| 420 |
},
|
| 421 |
{
|
| 422 |
-
"model": "๐ฎ gpt-4.1-2025-04-14
|
| 423 |
"score": 0,
|
| 424 |
-
"detail_box_on_target":
|
| 425 |
"cracked_levels": "0,0,0"
|
| 426 |
},
|
| 427 |
{
|
| 428 |
-
"model": "๐ฎ gpt-4o-2024-11-20
|
| 429 |
"score": 0,
|
| 430 |
-
"detail_box_on_target":
|
| 431 |
"cracked_levels": "0,0,0"
|
| 432 |
},
|
| 433 |
{
|
| 434 |
-
"model": "๐ฎ o1-2024-12-17
|
| 435 |
"score": 2.33,
|
| 436 |
-
"detail_box_on_target":
|
| 437 |
"cracked_levels": "1,1,2"
|
| 438 |
},
|
| 439 |
{
|
| 440 |
-
"model": "๐ฎ o1-mini-2024-09-12
|
| 441 |
"score": 1.33,
|
| 442 |
-
"detail_box_on_target":
|
| 443 |
"cracked_levels": "0,1,0"
|
| 444 |
},
|
| 445 |
{
|
| 446 |
-
"model": "๐ฎ o3-2025-04-16
|
| 447 |
"score": 8,
|
| 448 |
-
"detail_box_on_target":
|
| 449 |
"cracked_levels": "5,3"
|
| 450 |
},
|
| 451 |
{
|
| 452 |
-
"model": "๐ฎ o4-mini-2025-04-16
|
| 453 |
"score": 5.33,
|
| 454 |
-
"detail_box_on_target":
|
| 455 |
-
"cracked_levels": "2,
|
| 456 |
},
|
| 457 |
{
|
| 458 |
"model": "random (x30)",
|
| 459 |
"score": 0,
|
| 460 |
-
"detail_box_on_target":
|
| 461 |
"cracked_levels": "0,0,0"
|
| 462 |
},
|
| 463 |
{
|
| 464 |
-
"model": "๐ฎ claude-opus-4-20250514
|
| 465 |
"score": 4,
|
| 466 |
-
"
|
|
|
|
| 467 |
},
|
| 468 |
{
|
| 469 |
-
"model": "๐ฎ claude-sonnet-4-20250514
|
| 470 |
"score": 3,
|
| 471 |
-
"
|
|
|
|
| 472 |
},
|
| 473 |
{
|
| 474 |
-
"model": "๐ฎ deepseek-r1-0528
|
| 475 |
"score": 4.67,
|
| 476 |
-
"
|
|
|
|
| 477 |
},
|
| 478 |
{
|
| 479 |
-
"model": "๐ฎ qwen3-235B-A22B-fp8
|
| 480 |
"score": 2.33,
|
| 481 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 482 |
}
|
| 483 |
]
|
| 484 |
},
|
|
@@ -486,79 +622,79 @@
|
|
| 486 |
"runs": 1,
|
| 487 |
"results": [
|
| 488 |
{
|
| 489 |
-
"model": "๐ฎ claude-3-5-sonnet-20241022
|
| 490 |
"score": 2,
|
| 491 |
"progress": "1:2/5",
|
| 492 |
"evaluator result": "1/3"
|
| 493 |
},
|
| 494 |
{
|
| 495 |
-
"model": "๐ฎ claude-3-7-sonnet-20250219
|
| 496 |
"score": 7,
|
| 497 |
"progress": "2:2/9",
|
| 498 |
"evaluator result": "5/11"
|
| 499 |
},
|
| 500 |
{
|
| 501 |
-
"model": "๐ฎ deepseek-r1-0120
|
| 502 |
"score": 0,
|
| 503 |
"progress": "0",
|
| 504 |
"evaluator result": "1/5"
|
| 505 |
},
|
| 506 |
{
|
| 507 |
-
"model": "๐ฎ gemini-2.5-flash-preview-04-17
|
| 508 |
"score": 4,
|
| 509 |
"progress": "1:4/5",
|
| 510 |
"evaluator result": "1/7"
|
| 511 |
},
|
| 512 |
{
|
| 513 |
-
"model": "๐ฎ gemini-2.5-pro-preview-05-06
|
| 514 |
"score": 7,
|
| 515 |
"progress": "2:2/9",
|
| 516 |
"evaluator result": "2/3"
|
| 517 |
},
|
| 518 |
{
|
| 519 |
-
"model": "๐ฎ grok-3-mini-beta
|
| 520 |
"score": 0,
|
| 521 |
"progress": "0",
|
| 522 |
"evaluator result": "0"
|
| 523 |
},
|
| 524 |
{
|
| 525 |
-
"model": "๐ฎ llama-4-maverick-17b-128e-instruct-fp8
|
| 526 |
"score": 0,
|
| 527 |
"progress": "0",
|
| 528 |
"evaluator result": "0"
|
| 529 |
},
|
| 530 |
{
|
| 531 |
-
"model": "๐ฎ gpt-4.1-2025-04-14
|
| 532 |
"score": 2,
|
| 533 |
"progress": "1:2/5",
|
| 534 |
"evaluator result": "2/3"
|
| 535 |
},
|
| 536 |
{
|
| 537 |
-
"model": "๐ฎ gpt-4o-2024-11-20
|
| 538 |
"score": 0,
|
| 539 |
"progress": "0",
|
| 540 |
"evaluator result": "0"
|
| 541 |
},
|
| 542 |
{
|
| 543 |
-
"model": "๐ฎ o1-2024-12-17
|
| 544 |
"score": 16,
|
| 545 |
"progress": "3: 2/8",
|
| 546 |
"evaluator result": "6/11"
|
| 547 |
},
|
| 548 |
{
|
| 549 |
-
"model": "๐ฎ o1-mini-2024-09-12
|
| 550 |
"score": 0,
|
| 551 |
"progress": "0",
|
| 552 |
"evaluator result": "1/5"
|
| 553 |
},
|
| 554 |
{
|
| 555 |
-
"model": "๐ฎ o3-2025-04-16
|
| 556 |
"score": 16,
|
| 557 |
"progress": "3: 2/8",
|
| 558 |
"evaluator result": "1/2"
|
| 559 |
},
|
| 560 |
{
|
| 561 |
-
"model": "๐ฎ o4-mini-2025-04-16
|
| 562 |
"score": 4,
|
| 563 |
"progress": "1:4/5",
|
| 564 |
"evaluator result": "2/5"
|
|
@@ -570,17 +706,17 @@
|
|
| 570 |
"evaluator result": "0"
|
| 571 |
},
|
| 572 |
{
|
| 573 |
-
"model": "๐ฎ claude-opus-4-20250514
|
| 574 |
"score": 6,
|
| 575 |
"details": "6"
|
| 576 |
},
|
| 577 |
{
|
| 578 |
-
"model": "๐ฎ claude-sonnet-4-20250514
|
| 579 |
"score": 3.67,
|
| 580 |
"details": "3,4,4"
|
| 581 |
},
|
| 582 |
{
|
| 583 |
-
"model": "๐ฎ gemini-2.5-flash-preview-05-20
|
| 584 |
"score": 4.33,
|
| 585 |
"details": "3,4,6"
|
| 586 |
}
|
|
|
|
| 3 |
"runs": 3,
|
| 4 |
"results": [
|
| 5 |
{
|
| 6 |
+
"model": "๐ฎ claude-3-5-sonnet-20241022",
|
| 7 |
"score": 1267.7,
|
| 8 |
+
"detail_data":"709,1532,1562",
|
| 9 |
"progress": "1-1"
|
| 10 |
},
|
| 11 |
{
|
| 12 |
+
"model": "๐ฎ claude-3-7-sonnet-20250219",
|
| 13 |
"score": 1418.7,
|
| 14 |
+
"detail_data":"2015,709,1532",
|
| 15 |
"progress": "1-1"
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"model": "๐ฎ gemini-2.5-flash-preview-04-17",
|
| 19 |
"score": 1385.0,
|
| 20 |
+
"detail_data":"1672,1266,1247",
|
| 21 |
"progress": "1-1"
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"model": "๐ฎ gemini-2.5-pro-preview-05-06",
|
| 25 |
"score": 1498.3,
|
| 26 |
+
"detail_data":"1561,1271,1663",
|
| 27 |
"progress": "1-1"
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"model": "๐ฎ llama-4-maverick-17b-128e-instruct-fp8",
|
| 31 |
"score": 1468.7,
|
| 32 |
+
"detail_data":"898,2008,1500",
|
| 33 |
"progress": "1-1"
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"model": "๐ฎ gpt-4.1-2025-04-14",
|
| 37 |
"score": 2126.3,
|
| 38 |
+
"detail_data":"1531,722,4126",
|
| 39 |
"progress": "1-1"
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"model": "๐ฎ gpt-4o-2024-11-20",
|
| 43 |
"score": 2047.3,
|
| 44 |
+
"detail_data":"2017,2590,1535",
|
| 45 |
"progress": "1-1"
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"model": "๐ฎ o1-2024-12-17",
|
| 49 |
"score": 855,
|
| 50 |
+
"detail_data":"855",
|
| 51 |
"progress": "1-1"
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"model": "๐ฎ o3-2025-04-16",
|
| 55 |
"score": 3445,
|
| 56 |
+
"detail_data":"3445",
|
| 57 |
"progress": "1-1"
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"model": "๐ฎ o4-mini-2025-04-16",
|
| 61 |
"score": 1448.0,
|
| 62 |
+
"detail_data":"1525,1263,1556",
|
| 63 |
"progress": "1-1"
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"model": "random (x30)",
|
| 67 |
"score": 986.97,
|
| 68 |
+
"detail_data":"986.97",
|
| 69 |
"progress": "1-1"
|
| 70 |
}
|
| 71 |
]
|
|
|
|
| 74 |
"runs": 3,
|
| 75 |
"results": [
|
| 76 |
{
|
| 77 |
+
"model": "๐ฎ claude-3-5-sonnet-20241022",
|
| 78 |
"score": 1914.67,
|
| 79 |
"details": "1352,2860,1532",
|
| 80 |
"highest_tail": 256
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"model": "๐ฎ claude-3-7-sonnet-20250219",
|
| 84 |
"score": 2624,
|
| 85 |
"details": "2560,3224,2088",
|
| 86 |
"highest_tail": 256
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"model": "๐ฎ deepseek-r1-0120",
|
| 90 |
"score": 1873.33,
|
| 91 |
"details": "700,1240,3680",
|
| 92 |
"highest_tail": 256
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"model": "๐ฎ gemini-2.5-flash-preview-04-17",
|
| 96 |
"score": 1697.33,
|
| 97 |
"details": "1304,1316,2472",
|
| 98 |
"highest_tail": 256
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"model": "๐ฎ gemini-2.5-pro-preview-05-06",
|
| 102 |
"score": 3586.67,
|
| 103 |
"details": "5300,2400,3060",
|
| 104 |
"highest_tail": 512
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"model": "๐ฎ grok-3-mini-beta",
|
| 108 |
"score": 4036,
|
| 109 |
"details": "6412,2492,3204",
|
| 110 |
"highest_tail": 512
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"model": "๐ฎ llama-4-maverick-17b-128e-instruct-fp8",
|
| 114 |
"score": 1586.67,
|
| 115 |
"details": "1404,1272,2084",
|
| 116 |
"highest_tail": 128
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"model": "๐ฎ gpt-4.1-2025-04-14",
|
| 120 |
"score": 1656,
|
| 121 |
"details": "1156,2664,1148",
|
| 122 |
"highest_tail": 256
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"model": "๐ฎ gpt-4o-2024-11-20",
|
| 126 |
"score": 1656,
|
| 127 |
"details": "1604,1284,2080",
|
| 128 |
"highest_tail": 256
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"model": "๐ฎ o1-2024-12-17",
|
| 132 |
"score": 7580,
|
| 133 |
"details": "7580",
|
| 134 |
"highest_tail": 512
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"model": "๐ฎ o1-mini-2024-09-12",
|
| 138 |
"score": 2757.33,
|
| 139 |
"details": "3132,2004,3136",
|
| 140 |
"highest_tail": 256
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"model": "๐ฎ o3-2025-04-16",
|
| 144 |
"score": 7120,
|
| 145 |
"details": "7120",
|
| 146 |
"highest_tail": 512
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"model": "๐ฎ o4-mini-2025-04-16",
|
| 150 |
"score": 4432.0,
|
| 151 |
"details": "4928,5456,2912",
|
| 152 |
"highest_tail": 512
|
|
|
|
| 158 |
"highest_tail": 128
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"model": "๐ฎ claude-opus-4-20250514",
|
| 162 |
"score": 3036.0,
|
| 163 |
"details": "3036.0",
|
| 164 |
"highest_tail": 256
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"model": "๐ฎ claude-sonnet-4-20250514",
|
| 168 |
"score": 3136,
|
| 169 |
+
"details": "2148, 2360, 4900",
|
| 170 |
"highest_tail": 256
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"model": "๐ฎ deepseek-r1-0528",
|
| 174 |
"score": 3330.0,
|
| 175 |
+
"details": "3260, 3400",
|
| 176 |
"highest_tail": 256
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"model": "๐ฎ qwen3-235B-A22B-fp8",
|
| 180 |
"score": 2144.0,
|
| 181 |
+
"details": "1436, 2556, 2440",
|
| 182 |
+
"highest_tail": 256
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"model": "๐ฎ grok-4-0709",
|
| 186 |
+
"score": 4650.7,
|
| 187 |
+
"details": "4120, 4080, 5752",
|
| 188 |
+
"highest_tail": 512
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"model": "๐ฎ kimi-k2-0711-preview",
|
| 192 |
+
"score": 1562.67,
|
| 193 |
+
"details": "2360, 1628, 700",
|
| 194 |
+
"highest_tail": 256
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"model": "๐ฎ glm-4.5",
|
| 198 |
+
"score": 1201.33,
|
| 199 |
+
"details": "1440, 1064, 1100",
|
| 200 |
+
"highest_tail": 128
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"model": "๐ฎ qwen3-235B-A22B-fp8-thinking",
|
| 204 |
+
"score": 2473.33,
|
| 205 |
+
"details": "1276, 5196, 948",
|
| 206 |
+
"highest_tail": 256
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"model": "๐ฎ gpt-oss-120b",
|
| 210 |
+
"score": 1973.33,
|
| 211 |
+
"details": "696, 3240, 1984",
|
| 212 |
+
"highest_tail": 256
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"model": "๐ฎ gpt-oss-20b",
|
| 216 |
+
"score": 2040.0,
|
| 217 |
+
"details": "1484, 1432, 3204",
|
| 218 |
"highest_tail": 256
|
| 219 |
}
|
| 220 |
]
|
|
|
|
| 223 |
"runs": 3,
|
| 224 |
"results": [
|
| 225 |
{
|
| 226 |
+
"model": "๐ฎ claude-3-5-sonnet-20241022",
|
| 227 |
"score": 14.7,
|
| 228 |
"details": "16,14,14"
|
| 229 |
},
|
| 230 |
{
|
| 231 |
+
"model": "๐ฎ claude-3-7-sonnet-20250219",
|
| 232 |
"score": 16.3,
|
| 233 |
"details": "19,15,15"
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"model": "๐ฎ deepseek-r1-0120",
|
| 237 |
"score": 14.3,
|
| 238 |
"details": "15,14,14"
|
| 239 |
},
|
| 240 |
{
|
| 241 |
+
"model": "๐ฎ gemini-2.5-flash-preview-04-17",
|
| 242 |
"score": 16.3,
|
| 243 |
"details": "20,14,15"
|
| 244 |
},
|
| 245 |
{
|
| 246 |
+
"model": "๐ฎ gemini-2.5-pro-preview-05-06",
|
| 247 |
"score": 23.3,
|
| 248 |
"details": "23,23,24"
|
| 249 |
},
|
| 250 |
{
|
| 251 |
+
"model": "๐ฎ grok-3-mini-beta",
|
| 252 |
"score": 21.3,
|
| 253 |
"details": "20,15,29"
|
| 254 |
},
|
| 255 |
{
|
| 256 |
+
"model": "๐ฎ llama-4-maverick-17b-128e-instruct-fp8",
|
| 257 |
"score": 10.3,
|
| 258 |
"details": "9,10,12"
|
| 259 |
},
|
| 260 |
{
|
| 261 |
+
"model": "๐ฎ gpt-4.1-2025-04-14",
|
| 262 |
"score": 13.7,
|
| 263 |
"details": "13,14,14"
|
| 264 |
},
|
| 265 |
{
|
| 266 |
+
"model": "๐ฎ gpt-4o-2024-11-20",
|
| 267 |
"score": 14,
|
| 268 |
"details": "18,11,13"
|
| 269 |
},
|
| 270 |
{
|
| 271 |
+
"model": "๐ฎ o1-2024-12-17",
|
| 272 |
"score": 35,
|
| 273 |
"details": "35"
|
| 274 |
},
|
| 275 |
{
|
| 276 |
+
"model": "๐ฎ o1-mini-2024-09-12",
|
| 277 |
"score": 11.7,
|
| 278 |
"details": "11,11,13"
|
| 279 |
},
|
| 280 |
{
|
| 281 |
+
"model": "๐ฎ o3-2025-04-16",
|
| 282 |
"score": 42,
|
| 283 |
"details": "42"
|
| 284 |
},
|
| 285 |
{
|
| 286 |
+
"model": "๐ฎ o4-mini-2025-04-16",
|
| 287 |
"score": 25.3,
|
| 288 |
"details": "22,35,19"
|
| 289 |
},
|
|
|
|
| 293 |
"details": ""
|
| 294 |
},
|
| 295 |
{
|
| 296 |
+
"model": "๐ฎ claude-opus-4-20250514",
|
| 297 |
"score": 20,
|
| 298 |
"details": "17,18,25"
|
| 299 |
},
|
| 300 |
{
|
| 301 |
+
"model": "๐ฎ claude-sonnet-4-20250514",
|
| 302 |
"score": 19.33,
|
| 303 |
"details": "20,17,21"
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"model": "๐ฎ deepseek-r1-0528",
|
| 307 |
"score": 33.67,
|
| 308 |
"details": "26,34,41"
|
| 309 |
},
|
| 310 |
{
|
| 311 |
+
"model": "๐ฎ qwen3-235B-A22B-fp8",
|
| 312 |
"score": 11.67,
|
| 313 |
"details": "13,14,8"
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"model": "๐ฎ grok-4-0709",
|
| 317 |
+
"score": 125.67,
|
| 318 |
+
"details": "229,105,43"
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"model": "๐ฎ kimi-k2-0711-preview",
|
| 322 |
+
"score": 17,
|
| 323 |
+
"details": "20,15,16"
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"model": "๐ฎ glm-4.5",
|
| 327 |
+
"score": 19.67,
|
| 328 |
+
"details": "21, 21, 17"
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"model": "๐ฎ qwen3-235B-A22B-fp8-thinking",
|
| 332 |
+
"score": 16,
|
| 333 |
+
"details": "23,9,16"
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"model": "๐ฎ gpt-oss-120b",
|
| 337 |
+
"score": 12.67,
|
| 338 |
+
"details": "12, 13, 13"
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"model": "๐ฎ gpt-oss-20b",
|
| 342 |
+
"score": 14.33,
|
| 343 |
+
"details": "14, 13, 16"
|
| 344 |
}
|
| 345 |
]
|
| 346 |
},
|
|
|
|
| 348 |
"runs": 3,
|
| 349 |
"results": [
|
| 350 |
{
|
| 351 |
+
"model": "๐ฎ claude-3-5-sonnet-20241022",
|
| 352 |
"score": 106,
|
| 353 |
"details": "92,165,61"
|
| 354 |
},
|
| 355 |
{
|
| 356 |
+
"model": "๐ฎ claude-3-7-sonnet-20250219",
|
| 357 |
"score": 484,
|
| 358 |
"details": "535,428,489"
|
| 359 |
},
|
| 360 |
{
|
| 361 |
+
"model": "๐ฎ deepseek-r1-0120",
|
| 362 |
"score": 447.3,
|
| 363 |
"details": "409,436,497"
|
| 364 |
},
|
| 365 |
{
|
| 366 |
+
"model": "๐ฎ gemini-2.5-flash-preview-04-17",
|
| 367 |
"score": 334.7,
|
| 368 |
"details": "259,372,373"
|
| 369 |
},
|
| 370 |
{
|
| 371 |
+
"model": "๐ฎ gemini-2.5-pro-preview-05-06",
|
| 372 |
"score": 416.3,
|
| 373 |
"details": "411,414,424"
|
| 374 |
},
|
| 375 |
{
|
| 376 |
+
"model": "๐ฎ grok-3-mini-beta",
|
| 377 |
"score": 254,
|
| 378 |
"details": "299,332,131"
|
| 379 |
},
|
| 380 |
{
|
| 381 |
+
"model": "๐ฎ llama-4-maverick-17b-128e-instruct-fp8",
|
| 382 |
"score": 128.7,
|
| 383 |
"details": "67,139,180"
|
| 384 |
},
|
| 385 |
{
|
| 386 |
+
"model": "๐ฎ gpt-4.1-2025-04-14",
|
| 387 |
"score": 182,
|
| 388 |
"details": "163,215,168"
|
| 389 |
},
|
| 390 |
{
|
| 391 |
+
"model": "๐ฎ gpt-4o-2024-11-20",
|
| 392 |
"score": 147.3,
|
| 393 |
"details": "131,104,207"
|
| 394 |
},
|
| 395 |
{
|
| 396 |
+
"model": "๐ฎ o1-2024-12-17",
|
| 397 |
"score": 159,
|
| 398 |
"details": "159"
|
| 399 |
},
|
| 400 |
{
|
| 401 |
+
"model": "๐ฎ o1-mini-2024-09-12",
|
| 402 |
"score": 48,
|
| 403 |
"details": "21,86,37"
|
| 404 |
},
|
| 405 |
{
|
| 406 |
+
"model": "๐ฎ o3-2025-04-16",
|
| 407 |
"score": 647,
|
| 408 |
"details": "647"
|
| 409 |
},
|
| 410 |
{
|
| 411 |
+
"model": "๐ฎ o4-mini-2025-04-16",
|
| 412 |
"score": 487.3,
|
| 413 |
"details": "259,591,612"
|
| 414 |
},
|
|
|
|
| 418 |
"details": ""
|
| 419 |
},
|
| 420 |
{
|
| 421 |
+
"model": "๐ฎ claude-opus-4-20250514",
|
| 422 |
"score": 464,
|
| 423 |
"details": "593,406,393"
|
| 424 |
},
|
| 425 |
{
|
| 426 |
+
"model": "๐ฎ claude-sonnet-4-20250514",
|
| 427 |
"score": 478.33,
|
| 428 |
"details": "545,468,422"
|
| 429 |
},
|
| 430 |
{
|
| 431 |
+
"model": "๐ฎ deepseek-r1-0528",
|
| 432 |
"score": 491.67,
|
| 433 |
"details": "464,463,548"
|
| 434 |
},
|
| 435 |
{
|
| 436 |
+
"model": "๐ฎ qwen3-235B-A22B-fp8",
|
| 437 |
"score": 363.33,
|
| 438 |
"details": "365,372,353"
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"model": "๐ฎ grok-4-0709",
|
| 442 |
+
"score": 616.7,
|
| 443 |
+
"details": "586,730,534"
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"model": "๐ฎ kimi-k2-0711-preview",
|
| 447 |
+
"score": 101,
|
| 448 |
+
"details": "144,31,128"
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"model": "๐ฎ glm-4.5",
|
| 452 |
+
"score": 324.33,
|
| 453 |
+
"details": "377, 320, 276"
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"model": "๐ฎ qwen3-235B-A22B-fp8-thinking",
|
| 457 |
+
"score": 437,
|
| 458 |
+
"details": "511, 437, 363"
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"model": "๐ฎ gpt-oss-120b",
|
| 462 |
+
"score": 441.33,
|
| 463 |
+
"details": "377, 536, 411"
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"model": "๐ฎ gpt-oss-20b",
|
| 467 |
+
"score": 249.67,
|
| 468 |
+
"details": "243, 262, 244"
|
| 469 |
}
|
| 470 |
]
|
| 471 |
},
|
|
|
|
| 473 |
"runs": 3,
|
| 474 |
"results": [
|
| 475 |
{
|
| 476 |
+
"model": "๐ฎ claude-3-5-sonnet-20241022",
|
| 477 |
"score": 0,
|
| 478 |
+
"detail_box_on_target":"0,0,0",
|
| 479 |
"cracked_levels": "0,0,0"
|
| 480 |
},
|
| 481 |
{
|
| 482 |
+
"model": "๐ฎ claude-3-7-sonnet-20250219",
|
| 483 |
"score": 2.33,
|
| 484 |
+
"detail_box_on_target":"2,4,1",
|
| 485 |
"cracked_levels": "1,2,0"
|
| 486 |
},
|
| 487 |
{
|
| 488 |
+
"model": "๐ฎ deepseek-r1-0120",
|
| 489 |
"score": 1.33,
|
| 490 |
+
"detail_box_on_target":"2,0,2",
|
| 491 |
"cracked_levels": "1,0,1"
|
| 492 |
},
|
| 493 |
{
|
| 494 |
+
"model": "๐ฎ gemini-2.5-flash-preview-04-17",
|
| 495 |
"score": 1.67,
|
| 496 |
+
"detail_box_on_target":"3,0,2",
|
| 497 |
"cracked_levels": "2,0,1"
|
| 498 |
},
|
| 499 |
{
|
| 500 |
+
"model": "๐ฎ gemini-2.5-pro-preview-05-06",
|
| 501 |
"score": 4.33,
|
| 502 |
+
"detail_box_on_target":"4,4,5",
|
| 503 |
"cracked_levels": "2,2,3"
|
| 504 |
},
|
| 505 |
{
|
| 506 |
+
"model": "๐ฎ grok-3-mini-beta",
|
| 507 |
"score": 5.67,
|
| 508 |
+
"detail_box_on_target":"5,6,6",
|
| 509 |
"cracked_levels": "3,3,3"
|
| 510 |
},
|
| 511 |
{
|
| 512 |
+
"model": "๐ฎ llama-4-maverick-17b-128e-instruct-fp8",
|
| 513 |
"score": 0,
|
| 514 |
+
"detail_box_on_target":"0,0,0",
|
| 515 |
"cracked_levels": "0,0,0"
|
| 516 |
},
|
| 517 |
{
|
| 518 |
+
"model": "๐ฎ gpt-4.1-2025-04-14",
|
| 519 |
"score": 0,
|
| 520 |
+
"detail_box_on_target":"0,0,0",
|
| 521 |
"cracked_levels": "0,0,0"
|
| 522 |
},
|
| 523 |
{
|
| 524 |
+
"model": "๐ฎ gpt-4o-2024-11-20",
|
| 525 |
"score": 0,
|
| 526 |
+
"detail_box_on_target":"0,0,0",
|
| 527 |
"cracked_levels": "0,0,0"
|
| 528 |
},
|
| 529 |
{
|
| 530 |
+
"model": "๐ฎ o1-2024-12-17",
|
| 531 |
"score": 2.33,
|
| 532 |
+
"detail_box_on_target":"2,2,3",
|
| 533 |
"cracked_levels": "1,1,2"
|
| 534 |
},
|
| 535 |
{
|
| 536 |
+
"model": "๐ฎ o1-mini-2024-09-12",
|
| 537 |
"score": 1.33,
|
| 538 |
+
"detail_box_on_target":"1,2,1",
|
| 539 |
"cracked_levels": "0,1,0"
|
| 540 |
},
|
| 541 |
{
|
| 542 |
+
"model": "๐ฎ o3-2025-04-16",
|
| 543 |
"score": 8,
|
| 544 |
+
"detail_box_on_target":"10,6",
|
| 545 |
"cracked_levels": "5,3"
|
| 546 |
},
|
| 547 |
{
|
| 548 |
+
"model": "๐ฎ o4-mini-2025-04-16",
|
| 549 |
"score": 5.33,
|
| 550 |
+
"detail_box_on_target":"4,6,6",
|
| 551 |
+
"cracked_levels": "2,3,3"
|
| 552 |
},
|
| 553 |
{
|
| 554 |
"model": "random (x30)",
|
| 555 |
"score": 0,
|
| 556 |
+
"detail_box_on_target":"0,0,0",
|
| 557 |
"cracked_levels": "0,0,0"
|
| 558 |
},
|
| 559 |
{
|
| 560 |
+
"model": "๐ฎ claude-opus-4-20250514",
|
| 561 |
"score": 4,
|
| 562 |
+
"detail_box_on_target": "4,4,4",
|
| 563 |
+
"cracked_levels": "2,2,2"
|
| 564 |
},
|
| 565 |
{
|
| 566 |
+
"model": "๐ฎ claude-sonnet-4-20250514",
|
| 567 |
"score": 3,
|
| 568 |
+
"detail_box_on_target": "2,2,5",
|
| 569 |
+
"cracked_levels": "1,1,3"
|
| 570 |
},
|
| 571 |
{
|
| 572 |
+
"model": "๐ฎ deepseek-r1-0528",
|
| 573 |
"score": 4.67,
|
| 574 |
+
"detail_box_on_target": "4,4,6",
|
| 575 |
+
"cracked_levels": "2,2,3"
|
| 576 |
},
|
| 577 |
{
|
| 578 |
+
"model": "๐ฎ qwen3-235B-A22B-fp8",
|
| 579 |
"score": 2.33,
|
| 580 |
+
"detail_box_on_target": "1,2,4",
|
| 581 |
+
"cracked_levels": "0,1,2"
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"model": "๐ฎ grok-4-0709",
|
| 585 |
+
"score": 6.33,
|
| 586 |
+
"detail_box_on_target": "6,6,7",
|
| 587 |
+
"cracked_levels": "3,3,4"
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"model": "๐ฎ kimi-k2-0711-preview",
|
| 591 |
+
"score": 0,
|
| 592 |
+
"detail_box_on_target": "0,0,0",
|
| 593 |
+
"cracked_levels": "0,0,0"
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"model": "๐ฎ glm-4.5",
|
| 597 |
+
"score": 0.33,
|
| 598 |
+
"detail_box_on_target": "0,1,0",
|
| 599 |
+
"cracked_levels": "0,0,0"
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"model": "๐ฎ qwen3-235B-A22B-fp8-thinking",
|
| 603 |
+
"score": 5.33,
|
| 604 |
+
"detail_box_on_target": "6,4,6",
|
| 605 |
+
"cracked_levels": "3,2,3"
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"model": "๐ฎ gpt-oss-120b",
|
| 609 |
+
"score": 4,
|
| 610 |
+
"detail_box_on_target": "4",
|
| 611 |
+
"cracked_levels": "2"
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"model": "๐ฎ gpt-oss-20b",
|
| 615 |
+
"score": 4,
|
| 616 |
+
"detail_box_on_target": "4",
|
| 617 |
+
"cracked_levels": "2"
|
| 618 |
}
|
| 619 |
]
|
| 620 |
},
|
|
|
|
| 622 |
"runs": 1,
|
| 623 |
"results": [
|
| 624 |
{
|
| 625 |
+
"model": "๐ฎ claude-3-5-sonnet-20241022",
|
| 626 |
"score": 2,
|
| 627 |
"progress": "1:2/5",
|
| 628 |
"evaluator result": "1/3"
|
| 629 |
},
|
| 630 |
{
|
| 631 |
+
"model": "๐ฎ claude-3-7-sonnet-20250219",
|
| 632 |
"score": 7,
|
| 633 |
"progress": "2:2/9",
|
| 634 |
"evaluator result": "5/11"
|
| 635 |
},
|
| 636 |
{
|
| 637 |
+
"model": "๐ฎ deepseek-r1-0120",
|
| 638 |
"score": 0,
|
| 639 |
"progress": "0",
|
| 640 |
"evaluator result": "1/5"
|
| 641 |
},
|
| 642 |
{
|
| 643 |
+
"model": "๐ฎ gemini-2.5-flash-preview-04-17",
|
| 644 |
"score": 4,
|
| 645 |
"progress": "1:4/5",
|
| 646 |
"evaluator result": "1/7"
|
| 647 |
},
|
| 648 |
{
|
| 649 |
+
"model": "๐ฎ gemini-2.5-pro-preview-05-06",
|
| 650 |
"score": 7,
|
| 651 |
"progress": "2:2/9",
|
| 652 |
"evaluator result": "2/3"
|
| 653 |
},
|
| 654 |
{
|
| 655 |
+
"model": "๐ฎ grok-3-mini-beta",
|
| 656 |
"score": 0,
|
| 657 |
"progress": "0",
|
| 658 |
"evaluator result": "0"
|
| 659 |
},
|
| 660 |
{
|
| 661 |
+
"model": "๐ฎ llama-4-maverick-17b-128e-instruct-fp8",
|
| 662 |
"score": 0,
|
| 663 |
"progress": "0",
|
| 664 |
"evaluator result": "0"
|
| 665 |
},
|
| 666 |
{
|
| 667 |
+
"model": "๐ฎ gpt-4.1-2025-04-14",
|
| 668 |
"score": 2,
|
| 669 |
"progress": "1:2/5",
|
| 670 |
"evaluator result": "2/3"
|
| 671 |
},
|
| 672 |
{
|
| 673 |
+
"model": "๐ฎ gpt-4o-2024-11-20",
|
| 674 |
"score": 0,
|
| 675 |
"progress": "0",
|
| 676 |
"evaluator result": "0"
|
| 677 |
},
|
| 678 |
{
|
| 679 |
+
"model": "๐ฎ o1-2024-12-17",
|
| 680 |
"score": 16,
|
| 681 |
"progress": "3: 2/8",
|
| 682 |
"evaluator result": "6/11"
|
| 683 |
},
|
| 684 |
{
|
| 685 |
+
"model": "๐ฎ o1-mini-2024-09-12",
|
| 686 |
"score": 0,
|
| 687 |
"progress": "0",
|
| 688 |
"evaluator result": "1/5"
|
| 689 |
},
|
| 690 |
{
|
| 691 |
+
"model": "๐ฎ o3-2025-04-16",
|
| 692 |
"score": 16,
|
| 693 |
"progress": "3: 2/8",
|
| 694 |
"evaluator result": "1/2"
|
| 695 |
},
|
| 696 |
{
|
| 697 |
+
"model": "๐ฎ o4-mini-2025-04-16",
|
| 698 |
"score": 4,
|
| 699 |
"progress": "1:4/5",
|
| 700 |
"evaluator result": "2/5"
|
|
|
|
| 706 |
"evaluator result": "0"
|
| 707 |
},
|
| 708 |
{
|
| 709 |
+
"model": "๐ฎ claude-opus-4-20250514",
|
| 710 |
"score": 6,
|
| 711 |
"details": "6"
|
| 712 |
},
|
| 713 |
{
|
| 714 |
+
"model": "๐ฎ claude-sonnet-4-20250514",
|
| 715 |
"score": 3.67,
|
| 716 |
"details": "3,4,4"
|
| 717 |
},
|
| 718 |
{
|
| 719 |
+
"model": "๐ฎ gemini-2.5-flash-preview-05-20",
|
| 720 |
"score": 4.33,
|
| 721 |
"details": "3,4,6"
|
| 722 |
}
|