Skip to content

Benchmarks

Sources
8
Entries tracked
22,310
Last sync
29 min
All sources syncing normally
  • Arena · Text7 hours ago
  • Arena · WebDev7 hours ago
  • Arena · Vision7 hours ago
  • Arena · Agent7 hours ago
  • GPQA Diamond29 minutes ago
  • SWE-bench29 minutes ago
  • Terminal-Bench29 minutes ago
  • ARC-AGI-229 minutes ago
IFBench (Artificial Analysis) ×18 of 324 models
ModelOrg± CISwingAdd to compare
195DeepSeek R1 0528 (May '25)deepseekMay 2025$0.50 / $2.1539.6%—#88–250
203DeepSeek R1 (Jan '25)deepseekJan 2025$0.70 / $2.5039.0%—#117–389
282DeepSeek R1 Distill Llama 70BdeepseekJan 2025$0.80 / $0.8027.6%—#286–643
304DeepSeek R1 Distill Qwen 32Bdeepseek——22.9%—#255–778
308DeepSeek R1 Distill Qwen 14Bdeepseek——22.1%—#347–812
317DeepSeek R1 0528 Qwen3 8Bdeepseek——19.9%—#465–919
320DeepSeek R1 Distill Llama 8Bdeepseek——17.6%——
323DeepSeek R1 Distill Qwen 1.5Bdeepseek——13.2%—#407–1029

Showing IFBench (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.