Skip to content

Benchmarks

Sources
8
Entries tracked
22,308
Last sync
26 min
All sources syncing normally
  • Arena · Text10 hours ago
  • Arena · WebDev10 hours ago
  • Arena · Vision10 hours ago
  • Arena · Agent10 hours ago
  • GPQA Diamond26 minutes ago
  • SWE-bench26 minutes ago
  • Terminal-Bench26 minutes ago
  • ARC-AGI-226 minutes ago
AIME (math) ×13 of 200 models
ModelOrg± CISwingAdd to compare
75claude-sonnet-4-6AnthropicSep 2026$3 / $1585.8%81.3%–90.3%#38–77
89claude-sonnet-4-5-20250929AnthropicSep 2025$3 / $1577.8%71.5%–84.0%#66–232
96claude-sonnet-4-20250514AnthropicMay 2025—71.1%64.3%–77.9%#78–436

Showing AIME (math) 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.