Skip to content

Benchmarks

Sources
8
Entries tracked
22,308
Last sync
13 min
All sources syncing normally
  • Arena · Text10 hours ago
  • Arena · WebDev10 hours ago
  • Arena · Vision10 hours ago
  • Arena · Agent10 hours ago
  • GPQA Diamond13 minutes ago
  • SWE-bench13 minutes ago
  • Terminal-Bench13 minutes ago
  • ARC-AGI-213 minutes ago
Agent Arena ×11 of 55 models
ModelOrg± CISwingAdd to compare
31DeepSeek V4 Pro (High) (0813)deepseekAug 2026$0.66 / $1.980.004-0.014–0.021#17–54

Showing Agent Arena exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.

The few things in AI and quantum that actually mattered this week — honestly summarised.

One email a week. Unsubscribe in one click. No tracking, no sharing.