Skip to content

Benchmarks

Sources
8
Entries tracked
22,308
Last sync
14 min
All sources syncing normally
  • Arena · Text11 hours ago
  • Arena · WebDev11 hours ago
  • Arena · Vision11 hours ago
  • Arena · Agent11 hours ago
  • GPQA Diamond14 minutes ago
  • SWE-bench14 minutes ago
  • Terminal-Bench14 minutes ago
  • ARC-AGI-214 minutes ago
LiveCodeBench (Artificial Analysis) ×17 of 262 models
ModelOrg± CISwingAdd to compare
3DeepSeek V3.2 Specialedeepseek——89.6%——
10DeepSeek V3.2 (Reasoning)deepseekDec 2025$0.28 / $0.4286.2%—#86–247
27DeepSeek V3.1 Terminus (Reasoning)deepseekSep 2025$0.27 / $179.8%—#55–168
28DeepSeek V3.2 Exp (Reasoning)deepseekSep 2025$0.27 / $0.4178.9%—#92–334
31DeepSeek V3.1 (Reasoning)deepseekAug 2025—78.4%—#101–158
133DeepSeek V3 0324deepseekMar 2025—40.5%—#137–401
141DeepSeek V3 (Dec '24)deepseekDec 2024—35.9%—#178–644

Showing LiveCodeBench (Artificial Analysis) 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.