Skip to content

Benchmarks

Sources
8
Entries tracked
22,310
Last sync
42 min
All sources syncing normally
  • Arena · Text1 hour ago
  • Arena · WebDev1 hour ago
  • Arena · Vision1 hour ago
  • Arena · Agent1 hour ago
  • GPQA Diamond42 minutes ago
  • SWE-bench42 minutes ago
  • Terminal-Bench42 minutes ago
  • ARC-AGI-242 minutes ago

DeepSeek-V3

1.7%±0.8%

1.0%CI2.5%

DeepSeekDec 2024swing #178–#644

FrontierMath ×12 of 69 models
ModelOrg± CISwingAdd to compare
27fireworks/deepseek-v3p2DeepSeek——22.1%18.0%–26.2%—
56DeepSeek-V3DeepSeekDec 2024—1.7%1.0%–2.5%#178–644

Showing FrontierMath 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.