Skip to content

Benchmarks

Sources
8
Entries tracked
22,308
Last sync
10 min
All sources syncing normally
  • Arena · Text9 hours ago
  • Arena · WebDev9 hours ago
  • Arena · Vision9 hours ago
  • Arena · Agent9 hours ago
  • GPQA Diamond10 minutes ago
  • SWE-bench10 minutes ago
  • Terminal-Bench10 minutes ago
  • ARC-AGI-210 minutes ago

glm-5.3-flash

65.8%

no interval published

Z.ai (Zhipu AI)Aug 2026swing #26–#60

glm-5.2

22.8%

no interval published

Z.ai (Zhipu AI)Jun 2026swing #9–#49

glm-5

4.9%

no interval published

Z.ai (Zhipu AI)Feb 2026swing #57–#153

ARC-AGI-2 ×13 of 89 models
ModelOrg± CISwingAdd to compare
24glm-5.3-flashZ.ai (Zhipu AI)Aug 2026$0.05 / $0.2065.8%—#26–60
43glm-5.2Z.ai (Zhipu AI)Jun 2026$0.62 / $2.4222.8%—#9–49
60glm-5Z.ai (Zhipu AI)Feb 2026$1 / $3.204.9%—#57–153

Showing ARC-AGI-2 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.