Skip to content

Benchmarks

Sources
8
Entries tracked
22,318
Last sync
36 min
All sources syncing normally
  • Arena · Text57 minutes ago
  • Arena · WebDev57 minutes ago
  • Arena · Vision57 minutes ago
  • Arena · Agent56 minutes ago
  • GPQA Diamond36 minutes ago
  • SWE-bench36 minutes ago
  • Terminal-Bench36 minutes ago
  • ARC-AGI-236 minutes ago

grok-2-1212

48.1%

no interval published

xAIswing #291–#949

grok-2

46.5%

no interval published

xAIAug 2024swing #211–#623

grok-2-mini

45.5%

no interval published

xAIAug 2024swing #254–#618

LiveBench ×13 of 291 models
ModelOrg± CISwingAdd to compare
177grok-2-1212xAI——48.1%—#291–949
186grok-2xAIAug 2024—46.5%—#211–623
192grok-2-minixAIAug 2024—45.5%—#254–618

Showing LiveBench 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.