Skip to content

Benchmarks

Sources
8
Entries tracked
22,310
Last sync
5 min
All sources syncing normally
  • Arena · Text3 hours ago
  • Arena · WebDev3 hours ago
  • Arena · Vision3 hours ago
  • Arena · Agent3 hours ago
  • GPQA Diamond5 minutes ago
  • SWE-bench5 minutes ago
  • Terminal-Bench5 minutes ago
  • ARC-AGI-25 minutes ago
Vision Arena ×14 of 150 models
ModelOrg± CISwingAdd to compare
64gemini-2.5-flash-preview-09-2025googleSep 2025—1,2291,219–1,239#141–383
72gemini-2.5-flashgoogleJun 2025$0.30 / $2.501,2151,211–1,220#133–389
88gemini-2.5-flash-lite-preview-06-17-thinkinggoogleJan 2026—1,1881,181–1,196#159–426
93gemini-2.5-flash-lite-preview-09-2025-no-thinkinggoogleSep 2025—1,1751,165–1,184#170–613

Showing Vision 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.