Spaces:
Sleeping
Sleeping
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <title>OpenEnv Benchmark Report</title> | |
| <style> | |
| :root { | |
| --bg-primary: #0f172a; | |
| --bg-secondary: #1e293b; | |
| --bg-card: #1e293b; | |
| --text-primary: #f1f5f9; | |
| --text-secondary: #94a3b8; | |
| --accent: #6366f1; | |
| --accent-glow: rgba(99, 102, 241, 0.3); | |
| --success: #10b981; | |
| --warning: #f59e0b; | |
| --danger: #ef4444; | |
| --border: #334155; | |
| } | |
| * { margin: 0; padding: 0; box-sizing: border-box; } | |
| body { | |
| font-family: 'Inter', 'Segoe UI', system-ui, sans-serif; | |
| background: var(--bg-primary); | |
| color: var(--text-primary); | |
| line-height: 1.6; | |
| min-height: 100vh; | |
| } | |
| .container { max-width: 1200px; margin: 0 auto; padding: 2rem; } | |
| header { | |
| text-align: center; | |
| padding: 3rem 0 2rem; | |
| background: linear-gradient(135deg, var(--bg-primary) 0%, #1a1a3e 100%); | |
| border-bottom: 1px solid var(--border); | |
| margin-bottom: 2rem; | |
| } | |
| header h1 { | |
| font-size: 2.2rem; | |
| background: linear-gradient(135deg, #6366f1, #8b5cf6, #a78bfa); | |
| -webkit-background-clip: text; | |
| -webkit-text-fill-color: transparent; | |
| margin-bottom: 0.5rem; | |
| } | |
| header p { color: var(--text-secondary); font-size: 1.1rem; } | |
| .cards-grid { | |
| display: grid; | |
| grid-template-columns: repeat(auto-fit, minmax(220px, 1fr)); | |
| gap: 1.2rem; | |
| margin-bottom: 2.5rem; | |
| } | |
| .agent-card { | |
| background: var(--bg-card); | |
| border: 1px solid var(--border); | |
| border-radius: 12px; | |
| overflow: hidden; | |
| transition: transform 0.2s, box-shadow 0.2s; | |
| } | |
| .agent-card:hover { | |
| transform: translateY(-4px); | |
| box-shadow: 0 8px 30px rgba(0,0,0,0.3); | |
| } | |
| .agent-card-header { | |
| padding: 1rem 1.2rem 0.8rem; | |
| } | |
| .agent-card-header h3 { font-size: 1.1rem; } | |
| .agent-card-body { | |
| padding: 0.8rem 1.2rem 1.2rem; | |
| display: flex; | |
| gap: 2rem; | |
| } | |
| .metric { text-align: center; } | |
| .metric-val { font-size: 1.8rem; font-weight: 700; display: block; } | |
| .metric-label { font-size: 0.75rem; color: var(--text-secondary); text-transform: uppercase; letter-spacing: 0.05em; } | |
| table { | |
| width: 100%; | |
| border-collapse: collapse; | |
| background: var(--bg-card); | |
| border-radius: 12px; | |
| overflow: hidden; | |
| border: 1px solid var(--border); | |
| margin-bottom: 2.5rem; | |
| } | |
| th { | |
| padding: 1rem; | |
| text-align: left; | |
| font-size: 0.8rem; | |
| text-transform: uppercase; | |
| letter-spacing: 0.05em; | |
| color: var(--text-secondary); | |
| border-bottom: 1px solid var(--border); | |
| background: rgba(99, 102, 241, 0.05); | |
| } | |
| td { | |
| padding: 0.85rem 1rem; | |
| border-bottom: 1px solid var(--border); | |
| font-size: 0.95rem; | |
| } | |
| tr:last-child td { border-bottom: none; } | |
| tr:hover { background: rgba(99, 102, 241, 0.05); } | |
| .agent-badge { | |
| background: var(--accent); | |
| color: white; | |
| padding: 0.25rem 0.75rem; | |
| border-radius: 20px; | |
| font-size: 0.8rem; | |
| font-weight: 600; | |
| } | |
| .score-bar-bg { | |
| width: 120px; | |
| height: 8px; | |
| background: var(--border); | |
| border-radius: 4px; | |
| display: inline-block; | |
| vertical-align: middle; | |
| margin-right: 0.5rem; | |
| } | |
| .score-bar { | |
| height: 100%; | |
| border-radius: 4px; | |
| transition: width 1s ease; | |
| } | |
| .score-val { font-weight: 600; font-variant-numeric: tabular-nums; } | |
| .chart-container { | |
| background: var(--bg-card); | |
| border: 1px solid var(--border); | |
| border-radius: 12px; | |
| padding: 2rem; | |
| margin-bottom: 2rem; | |
| } | |
| .chart-container h2 { | |
| margin-bottom: 1.5rem; | |
| font-size: 1.3rem; | |
| } | |
| canvas { max-width: 100%; } | |
| footer { | |
| text-align: center; | |
| padding: 2rem; | |
| color: var(--text-secondary); | |
| font-size: 0.85rem; | |
| } | |
| @keyframes fadeIn { | |
| from { opacity: 0; transform: translateY(20px); } | |
| to { opacity: 1; transform: translateY(0); } | |
| } | |
| .animated { animation: fadeIn 0.6s ease forwards; } | |
| </style> | |
| </head> | |
| <body> | |
| <header> | |
| <div class="container"> | |
| <h1>🏆 Benchmark Comparison Report</h1> | |
| <p>OpenEnv Data Pipeline Debugger — Agent Performance Analysis</p> | |
| </div> | |
| </header> | |
| <div class="container"> | |
| <h2 style="margin-bottom:1rem;color:var(--text-secondary);font-size:0.9rem;text-transform:uppercase;letter-spacing:0.05em;">Agent Summary</h2> | |
| <div class="cards-grid animated"> | |
| <div class="agent-card"> | |
| <div class="agent-card-header" style="border-bottom: 3px solid #f59e0b"> | |
| <h3>Random</h3> | |
| </div> | |
| <div class="agent-card-body"> | |
| <div class="metric"> | |
| <span class="metric-val" style="color:#f59e0b">0.3179</span> | |
| <span class="metric-label">Avg Score</span> | |
| </div> | |
| <div class="metric"> | |
| <span class="metric-val">23</span> | |
| <span class="metric-label">Avg Steps</span> | |
| </div> | |
| </div> | |
| </div> | |
| <div class="agent-card"> | |
| <div class="agent-card-header" style="border-bottom: 3px solid #ef4444"> | |
| <h3>Greedy</h3> | |
| </div> | |
| <div class="agent-card-body"> | |
| <div class="metric"> | |
| <span class="metric-val" style="color:#ef4444">0.2520</span> | |
| <span class="metric-label">Avg Score</span> | |
| </div> | |
| <div class="metric"> | |
| <span class="metric-val">8</span> | |
| <span class="metric-label">Avg Steps</span> | |
| </div> | |
| </div> | |
| </div> | |
| <div class="agent-card"> | |
| <div class="agent-card-header" style="border-bottom: 3px solid #f59e0b"> | |
| <h3>Fixed-Strategy</h3> | |
| </div> | |
| <div class="agent-card-body"> | |
| <div class="metric"> | |
| <span class="metric-val" style="color:#f59e0b">0.4367</span> | |
| <span class="metric-label">Avg Score</span> | |
| </div> | |
| <div class="metric"> | |
| <span class="metric-val">13</span> | |
| <span class="metric-label">Avg Steps</span> | |
| </div> | |
| </div> | |
| </div></div> | |
| <h2 style="margin-bottom:1rem;color:var(--text-secondary);font-size:0.9rem;text-transform:uppercase;letter-spacing:0.05em;">Detailed Results</h2> | |
| <table class="animated" style="animation-delay:0.2s"> | |
| <thead> | |
| <tr> | |
| <th>Agent</th> | |
| <th>Task</th> | |
| <th>Score</th> | |
| <th>Steps</th> | |
| <th>Time</th> | |
| <th>Best</th> | |
| </tr> | |
| </thead> | |
| <tbody> | |
| <tr> | |
| <td><span class="agent-badge">Random</span></td> | |
| <td>Easy Schema Fix</td> | |
| <td> | |
| <div class="score-bar-bg"> | |
| <div class="score-bar" style="width:8.03%;background:#ef4444"></div> | |
| </div> | |
| <span class="score-val">0.0803</span> | |
| </td> | |
| <td>10</td> | |
| <td>0.111s</td> | |
| <td>0.1800</td> | |
| </tr> | |
| <tr> | |
| <td><span class="agent-badge">Random</span></td> | |
| <td>Medium Data Quality</td> | |
| <td> | |
| <div class="score-bar-bg"> | |
| <div class="score-bar" style="width:23.830000000000002%;background:#ef4444"></div> | |
| </div> | |
| <span class="score-val">0.2383</span> | |
| </td> | |
| <td>20</td> | |
| <td>0.151s</td> | |
| <td>0.3450</td> | |
| </tr> | |
| <tr> | |
| <td><span class="agent-badge">Random</span></td> | |
| <td>Hard Pipeline Orchestration</td> | |
| <td> | |
| <div class="score-bar-bg"> | |
| <div class="score-bar" style="width:63.5%;background:#f59e0b"></div> | |
| </div> | |
| <span class="score-val">0.6350</span> | |
| </td> | |
| <td>40</td> | |
| <td>0.415s</td> | |
| <td>0.9450</td> | |
| </tr> | |
| <tr> | |
| <td><span class="agent-badge">Greedy</span></td> | |
| <td>Easy Schema Fix</td> | |
| <td> | |
| <div class="score-bar-bg"> | |
| <div class="score-bar" style="width:2%;background:#ef4444"></div> | |
| </div> | |
| <span class="score-val">0.0010</span> | |
| </td> | |
| <td>7</td> | |
| <td>0.025s</td> | |
| <td>0.0010</td> | |
| </tr> | |
| <tr> | |
| <td><span class="agent-badge">Greedy</span></td> | |
| <td>Medium Data Quality</td> | |
| <td> | |
| <div class="score-bar-bg"> | |
| <div class="score-bar" style="width:14.000000000000002%;background:#ef4444"></div> | |
| </div> | |
| <span class="score-val">0.1400</span> | |
| </td> | |
| <td>5</td> | |
| <td>0.033s</td> | |
| <td>0.1400</td> | |
| </tr> | |
| <tr> | |
| <td><span class="agent-badge">Greedy</span></td> | |
| <td>Hard Pipeline Orchestration</td> | |
| <td> | |
| <div class="score-bar-bg"> | |
| <div class="score-bar" style="width:61.5%;background:#f59e0b"></div> | |
| </div> | |
| <span class="score-val">0.6150</span> | |
| </td> | |
| <td>12</td> | |
| <td>0.148s</td> | |
| <td>0.6150</td> | |
| </tr> | |
| <tr> | |
| <td><span class="agent-badge">Fixed-Strategy</span></td> | |
| <td>Easy Schema Fix</td> | |
| <td> | |
| <div class="score-bar-bg"> | |
| <div class="score-bar" style="width:9.0%;background:#ef4444"></div> | |
| </div> | |
| <span class="score-val">0.0900</span> | |
| </td> | |
| <td>10</td> | |
| <td>0.051s</td> | |
| <td>0.0900</td> | |
| </tr> | |
| <tr> | |
| <td><span class="agent-badge">Fixed-Strategy</span></td> | |
| <td>Medium Data Quality</td> | |
| <td> | |
| <div class="score-bar-bg"> | |
| <div class="score-bar" style="width:32.5%;background:#f59e0b"></div> | |
| </div> | |
| <span class="score-val">0.3250</span> | |
| </td> | |
| <td>12</td> | |
| <td>0.083s</td> | |
| <td>0.3250</td> | |
| </tr> | |
| <tr> | |
| <td><span class="agent-badge">Fixed-Strategy</span></td> | |
| <td>Hard Pipeline Orchestration</td> | |
| <td> | |
| <div class="score-bar-bg"> | |
| <div class="score-bar" style="width:89.5%;background:#10b981"></div> | |
| </div> | |
| <span class="score-val">0.8950</span> | |
| </td> | |
| <td>16</td> | |
| <td>0.136s</td> | |
| <td>0.9450</td> | |
| </tr></tbody> | |
| </table> | |
| <div class="chart-container animated" style="animation-delay:0.4s"> | |
| <h2>Score Comparison by Task</h2> | |
| <canvas id="barChart" height="300"></canvas> | |
| </div> | |
| </div> | |
| <footer> | |
| <p>Generated by OpenEnv Data Pipeline Debugger Benchmark Suite</p> | |
| </footer> | |
| <script> | |
| const data = {"Random": {"easy_schema_fix": 0.0803, "medium_data_quality": 0.2383, "hard_pipeline_orchestration": 0.635}, "Greedy": {"easy_schema_fix": 0.001, "medium_data_quality": 0.14, "hard_pipeline_orchestration": 0.615}, "Fixed-Strategy": {"easy_schema_fix": 0.09, "medium_data_quality": 0.325, "hard_pipeline_orchestration": 0.895}}; | |
| const canvas = document.getElementById('barChart'); | |
| const ctx = canvas.getContext('2d'); | |
| function drawChart() { | |
| const rect = canvas.getBoundingClientRect(); | |
| canvas.width = rect.width * 2; | |
| canvas.height = 600; | |
| ctx.scale(2, 2); | |
| const agents = Object.keys(data); | |
| const tasks = Object.keys(data[agents[0]] || {}); | |
| const colors = ['#ef4444', '#f59e0b', '#10b981', '#6366f1']; | |
| const barWidth = 30; | |
| const groupWidth = (agents.length * barWidth) + 20; | |
| const startX = 80; | |
| const chartHeight = 250; | |
| const startY = 270; | |
| // Y axis | |
| ctx.strokeStyle = '#334155'; | |
| ctx.lineWidth = 1; | |
| for (let i = 0; i <= 5; i++) { | |
| const y = startY - (i * chartHeight / 5); | |
| ctx.beginPath(); | |
| ctx.moveTo(startX, y); | |
| ctx.lineTo(startX + tasks.length * groupWidth + 20, y); | |
| ctx.stroke(); | |
| ctx.fillStyle = '#94a3b8'; | |
| ctx.font = '11px Inter, sans-serif'; | |
| ctx.textAlign = 'right'; | |
| ctx.fillText((i * 0.2).toFixed(1), startX - 10, y + 4); | |
| } | |
| // Bars | |
| tasks.forEach((task, ti) => { | |
| const groupX = startX + ti * groupWidth + 30; | |
| agents.forEach((agent, ai) => { | |
| const score = data[agent][task] || 0; | |
| const barH = score * chartHeight; | |
| const x = groupX + ai * barWidth; | |
| const y = startY - barH; | |
| ctx.fillStyle = colors[ai % colors.length]; | |
| ctx.beginPath(); | |
| ctx.roundRect(x, y, barWidth - 4, barH, [4, 4, 0, 0]); | |
| ctx.fill(); | |
| // Score label | |
| ctx.fillStyle = '#f1f5f9'; | |
| ctx.font = 'bold 10px Inter, sans-serif'; | |
| ctx.textAlign = 'center'; | |
| ctx.fillText(score.toFixed(2), x + (barWidth - 4) / 2, y - 6); | |
| }); | |
| // Task label | |
| ctx.fillStyle = '#94a3b8'; | |
| ctx.font = '11px Inter, sans-serif'; | |
| ctx.textAlign = 'center'; | |
| const labelX = groupX + (agents.length * barWidth) / 2; | |
| ctx.fillText(task.replace(/_/g, ' ').replace(/\b\w/g, c => c.toUpperCase()), labelX, startY + 20); | |
| }); | |
| // Legend | |
| const legendY = 10; | |
| agents.forEach((agent, i) => { | |
| const x = startX + i * 130; | |
| ctx.fillStyle = colors[i % colors.length]; | |
| ctx.fillRect(x, legendY, 14, 14); | |
| ctx.fillStyle = '#f1f5f9'; | |
| ctx.font = '12px Inter, sans-serif'; | |
| ctx.textAlign = 'left'; | |
| ctx.fillText(agent, x + 20, legendY + 12); | |
| }); | |
| } | |
| drawChart(); | |
| window.addEventListener('resize', () => { ctx.clearRect(0, 0, canvas.width, canvas.height); ctx.setTransform(1,0,0,1,0,0); drawChart(); }); | |
| </script> | |
| </body> | |
| </html> |