Skip to content

Benchmarks

Sources
8
Entries tracked
22,310
Last sync
17 min
All sources syncing normally
  • Arena · Text4 hours ago
  • Arena · WebDev4 hours ago
  • Arena · Vision4 hours ago
  • Arena · Agent4 hours ago
  • GPQA Diamond17 minutes ago
  • SWE-bench17 minutes ago
  • Terminal-Bench17 minutes ago
  • ARC-AGI-217 minutes ago
LiveBench ×18 of 291 models
ModelOrg± CISwingAdd to compare
45deepseek-v3.1-terminus-thinkingDeepSeekOct 2026—71.4%—#97–137
72deepseek-v3.2-thinkingDeepSeekOct 2026—66.2%—#103–344
82deepseek-v3.1-terminusDeepSeekSep 2025$0.27 / $164.7%—#55–168
87deepseek-v3.2-specialeDeepSeek——64.1%——
93deepseek-v3.2-exp-thinkingDeepSeekOct 2026—63.1%—#77–180
95deepseek-v3-0324DeepSeekMar 2025—62.8%—#137–401
107deepseek-v3DeepSeekDec 2024—60.5%—#178–644
133deepseek-v3.2-expDeepSeekSep 2025$0.27 / $0.4155.5%—#92–334

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.