Skip to content

Benchmarks

Sources
8
Entries tracked
22,318
Last sync
35 min
All sources syncing normally
  • Arena · Text3 hours ago
  • Arena · WebDev3 hours ago
  • Arena · Vision3 hours ago
  • Arena · Agent3 hours ago
  • GPQA Diamond35 minutes ago
  • SWE-bench35 minutes ago
  • Terminal-Bench35 minutes ago
  • ARC-AGI-235 minutes ago

deepseek-v3.2

1,437±3

1,434CI1,440

deepseekDec 2025swing #86–#247

Factuality Arena ×14 of 172 models
ModelOrg± CISwingAdd to compare
69deepseek-v3.2-exp-thinkingdeepseekOct 2026—1,4461,436–1,457#77–181
90deepseek-v3.2deepseekDec 2025$0.28 / $0.421,4371,434–1,440#86–247
92deepseek-v3.2-expdeepseekSep 2025$0.27 / $0.411,4361,430–1,442#92–334
102deepseek-v3.2-thinkingdeepseekOct 2026—1,4321,429–1,436#103–345

Showing Factuality 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.