Failed to load benchmark data
Could not fetch history.db. Make sure the file exists and you're serving this page via HTTP.
Dashboard Overview
Runs limit:
Model Intelligence Index
Intelligence vs. Throughput (Value Frontier)
Success Count per Run
Success Rate Over Time
Top 10 Fastest Models (Avg)
Top 10 Throughput (tok/s)
Model Reliability
Model Leaderboard
Ranked by composite score - click a row to explore that model
Runs limit:
| # ↓ | Model | Score ↓ | Uptime | Intel | Avg Time | Best Time | Throughput | Wins | Trend |
|---|
Select Model
Runs limit:
Model Capability Breakdown (Radar)
Model Performance vs. Global Average
Response Time History
Error Breakdown
Availability Heatmap
Run History (last 20)
| Timestamp | Status | Response Time | Tok/s |
|---|
Run Timeline
Model Comparison
Head-to-head analysis
Runs limit:
Head-to-Head Stats
Response Time Overlay
Win Timeline (per run)