Skip to content

Benchmarks

Sources
8
Entries tracked
22,308
Last sync
24 min
All sources syncing normally
  • Arena · Text10 hours ago
  • Arena · WebDev10 hours ago
  • Arena · Vision10 hours ago
  • Arena · Agent10 hours ago
  • GPQA Diamond24 minutes ago
  • SWE-bench24 minutes ago
  • Terminal-Bench24 minutes ago
  • ARC-AGI-224 minutes ago

DeepSeek-V3

15.8%±4.3%

11.5%CI20.2%

DeepSeekDec 2024swing #178–#644

AIME (math) ×12 of 200 models
ModelOrg± CISwingAdd to compare
131DeepSeek-V3-0324DeepSeekMar 2025—37.8%31.5%–44.0%#137–401
148DeepSeek-V3DeepSeekDec 2024—15.8%11.5%–20.2%#178–644

Showing AIME (math) 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.